© 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. 70678
    Prev
    Next
    INDEX
    Explanations

    written

    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
     membres
    -0.08
     Meg
    -0.07
    monthly
    -0.07
     toc
    -0.07
    "You
    -0.07
    /mod
    -0.07
     modele
    -0.07
     prophet
    -0.07
    -generic
    -0.07
     crossword
    -0.07
    POSITIVE LOGITS
    휙
    0.07
    ONT
    0.07
     HERO
    0.07
    胃口
    0.07
    六合
    0.07
    这样一来
    0.06
    SION
    0.06
    اه
    0.06
    yster
    0.06
    날
    0.06
    Activations Density 0.215%

    No Known Activations