© 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. 28704
    Prev
    Next
    INDEX
    Explanations

    flash

    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
     objet
    -0.08
    먕
    -0.07
    我国
    -0.07
    =label
    -0.07
    kategori
    -0.07
     opt
    -0.06
     мя
    -0.06
     endPoint
    -0.06
    EXIT
    -0.06
     own
    -0.06
    POSITIVE LOGITS
     flashy
    0.08
     flashback
    0.07
    paste
    0.07
    _ValueChanged
    0.07
     Flash
    0.07
    ={[
    0.07
     geschichten
    0.07
     Maze
    0.07
     flashed
    0.07
    成果转化
    0.07
    Activations Density 0.007%

    No Known Activations