© 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. 71629
    Prev
    Next
    INDEX
    Explanations

    measuring amounts of substances

    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
     vocalist
    -0.07
    蕭
    -0.07
     их
    -0.06
    怔
    -0.06
    ckill
    -0.06
     الرغم
    -0.06
     generates
    -0.06
    乐团
    -0.06
     verdad
    -0.06
     مليار
    -0.06
    POSITIVE LOGITS
     admirable
    0.07
    _oauth
    0.07
     TYPES
    0.07
     tubes
    0.06
    之前的
    0.06
    gap
    0.06
    ┇
    0.06
    afka
    0.06
    ,sizeof
    0.06
    -now
    0.06
    Activations Density 0.038%

    No Known Activations