© 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. Qwen3-4B
    5. 32-TRANSCODER-HP
    7. 41140
    Prev
    Next
    INDEX
    Explanations

    Countries and continents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    *B
    -0.28
     north
    -0.26
    Styles
    -0.26
    ENU
    -0.26
     Bu
    -0.26
    most
    -0.26
    对äºİæĪij们
    -0.25
     tongues
    -0.24
    yp
    -0.24
    ĶåĽŀ
    -0.24
    POSITIVE LOGITS
     hạ
    0.27
    ALA
    0.25
     gauche
    0.24
     fırsat
    0.24
     Labs
    0.24
    .Small
    0.23
    losed
    0.23
    è¾£
    0.23
    åѤ
    0.23
    åĪ¹éĤ£
    0.23
    Activations Density 0.002%

    No Known Activations