© 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. 123716
    Prev
    Next
    INDEX
    Explanations

    the

    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
    Virtual
    -0.07
    零售
    -0.07
     mild
    -0.07
    跟随
    -0.06
    uncture
    -0.06
    วก
    -0.06
    TC
    -0.06
     analyse
    -0.06
    رق
    -0.06
     verify
    -0.06
    POSITIVE LOGITS
    🚃
    0.07
    헵
    0.07
     יהודי
    0.07
    اتحاد
    0.07
    :UITableView
    0.07
    史上最
    0.07
    .getDocument
    0.07
     Hemisphere
    0.07
    生态圈
    0.07
    养老保险
    0.06
    Activations Density 0.002%

    No Known Activations