© 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. 11-RESID-POST-AA
    11. 57553
    Prev
    Next
    INDEX
    Explanations

    DataStream

    np_max-act · gemini-2.0-flash

    The neuron detects code-like and technical programming content — tokens that look like filenames/paths, code fragments, and software/documentation terminology.

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    حداث
    -0.08
    liśmy
    -0.07
     seleccion
    -0.06
    苉
    -0.06
     Dad
    -0.06
    RAR
    -0.06
     Hector
    -0.06
    /he
    -0.06
     comp
    -0.06
    挑战
    -0.06
    POSITIVE LOGITS
    .
    0.11
    ，
    0.09
    .↵↵
    0.08
    和
    0.08
    〳
    0.07
    .↵
    0.07
    :↵
    0.07
     &___
    0.07
    🧔
    0.07
     a
    0.07
    Activations Density 35.261%

    No Known Activations