© 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. 79518
    Prev
    Next
    INDEX
    Explanations

    *

    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
     TOUR
    -0.07
     AUTO
    -0.07
     initData
    -0.07
    Resp
    -0.06
     März
    -0.06
    迳
    -0.06
    着实
    -0.06
    咎
    -0.06
    >H
    -0.06
     divul
    -0.06
    POSITIVE LOGITS
     השא
    0.08
    ового
    0.07
    .curve
    0.07
    コンテン
    0.07
    东盟
    0.07
     ()->
    0.07
    抜け
    0.07
    _icons
    0.07
     thời
    0.07
    وحدة
    0.07
    Activations Density 0.017%

    No Known Activations