© 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 EvalsExportsAPI 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. 109371
    Prev
    Next
    INDEX
    Explanations

    Code/technical documentation

    np_max-act · gemini-2.0-flash

    the neuron detects numeric tokens—numbers, dates, and version-like digit sequences.

    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
    賓
    -0.08
    뒤
    -0.07
    associated
    -0.07
     receipt
    -0.07
    蛆
    -0.07
     phản
    -0.07
     ohio
    -0.07
    zeigen
    -0.07
     verschied
    -0.07
    [],
    -0.07
    POSITIVE LOGITS
    ows
    0.08
     última
    0.07
     BB
    0.07
     Runs
    0.07
    征战
    0.07
    alt
    0.07
     Carr
    0.06
    .urls
    0.06
    /etc
    0.06
    リ
    0.06
    Activations Density 1.115%

    No Known Activations