© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 51153
    Prev
    Next
    INDEX
    Explanations

    offensive content

    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
    Negative Logits
     ul
    -0.07
    	My
    -0.07
     convenient
    -0.07
     Tourism
    -0.06
    -vector
    -0.06
    ination
    -0.06
    .states
    -0.06
    uity
    -0.06
     lies
    -0.06
     בכלל
    -0.06
    POSITIVE LOGITS
     saúde
    0.09
    STS
    0.08
    YPD
    0.07
     può
    0.07
    되기
    0.07
    ♕
    0.07
     getContext
    0.07
    argo
    0.07
    LT
    0.07
     RTP
    0.07
    Activations Density 0.034%

    No Known Activations