© 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. 47073
    Prev
    Next
    INDEX
    Explanations

    math equations

    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
    إدارية
    -0.07
    ìm
    -0.07
    แนวทาง
    -0.07
    getDoctrine
    -0.07
    idée
    -0.07
    放弃
    -0.07
    mmc
    -0.07
    冬奥
    -0.07
    备战
    -0.07
     cet
    -0.06
    POSITIVE LOGITS
     ');↵
    0.08
     mounts
    0.07
     Bulg
    0.07
     urges
    0.07
    bons
    0.07
    -script
    0.07
     Yugoslavia
    0.07
    upid
    0.07
    -support
    0.06
     Parallel
    0.06
    Activations Density 0.009%

    No Known Activations