© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 44438
    Prev
    Next
    INDEX
    Explanations

    ellipsis

    np_max-act · gemini-2.0-flash

    The neuron activates on the starts of long multi-line content blocks—e.g., code samples, Q/A sections, or paragraph bodies—marking block-level text segments.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kéo
    -0.08
     Bre
    -0.07
     leider
    -0.07
     poisoned
    -0.07
    ader
    -0.07
     Ach
    -0.07
    (cps
    -0.07
     attracted
    -0.07
     TimeUnit
    -0.07
     Ren
    -0.07
    POSITIVE LOGITS
    ...↵↵
    0.07
     lights
    0.07
    海南省
    0.06
     fwd
    0.06
    ...\
    0.06
    ...↵
    0.06
    .POST
    0.06
    ccording
    0.06
    机械
    0.06
    电阻
    0.06
    Activations Density 0.044%

    No Known Activations