© 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. 23959
    Prev
    Next
    INDEX
    Explanations

    Articles

    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
    (binary
    -0.07
    农业科技
    -0.07
     çer
    -0.07
    髀
    -0.07
    韭
    -0.07
    (random
    -0.07
    县长
    -0.07
    .dense
    -0.07
    基石
    -0.07
     międz
    -0.07
    POSITIVE LOGITS
     [--
    0.07
    {↵
    0.07
    Com
    0.07
    Catalog
    0.06
    عزل
    0.06
    صوم
    0.06
     ACM
    0.06
     systems
    0.06
    קבע
    0.06
    }↵↵↵
    0.06
    Activations Density 0.016%

    No Known Activations