© 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. 19-RESID-POST-AA
    11. 70556
    Prev
    Next
    INDEX
    Explanations

    -time

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sust
    -0.07
    よ
    -0.07
     Avalanche
    -0.07
    ვ
    -0.07
    로서
    -0.07
     souvenir
    -0.07
    的眼睛
    -0.07
     безопасн
    -0.06
     Yö
    -0.06
     türl
    -0.06
    POSITIVE LOGITS
    ALTER
    0.07
    _prices
    0.07
    CKER
    0.07
    mart
    0.07
    厉害
    0.07
    oto
    0.06
     Seller
    0.06
    上世纪
    0.06
     policymakers
    0.06
    点击
    0.06
    Activations Density 0.003%

    No Known Activations