© 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. 7-RESID-POST-AA
    11. 81582
    Prev
    Next
    INDEX
    Explanations

    Legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .provider
    -0.07
    і
    -0.07
    province
    -0.07
    חשמל
    -0.07
    תנועה
    -0.06
    .bottomAnchor
    -0.06
    booking
    -0.06
    .energy
    -0.06
    ביניהם
    -0.06
    _staff
    -0.06
    POSITIVE LOGITS
    就在于
    0.09
    {T
    0.07
    .cleaned
    0.07
    QUIRE
    0.07
     runs
    0.07
    (g
    0.07
    产权
    0.07
    *>::
    0.07
    (id
    0.07
     {!
    0.07
    Activations Density 0.129%

    No Known Activations