© 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. 20120
    Prev
    Next
    INDEX
    Explanations

    tutorial

    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
    알
    -0.08
     of
    -0.08
    監
    -0.07
     Propel
    -0.07
    .Be
    -0.07
    .Topic
    -0.06
    roat
    -0.06
     clap
    -0.06
     Algebra
    -0.06
    日照
    -0.06
    POSITIVE LOGITS
    悲剧
    0.07
    Usually
    0.06
     tails
    0.06
     experimenting
    0.06
    tesy
    0.06
    .times
    0.06
    ᠪ
    0.06
    fallback
    0.06
     optimizing
    0.06
    削减
    0.06
    Activations Density 0.006%

    No Known Activations