© 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. 31-TRANSCODER-HP
    7. 19942
    Prev
    Next
    INDEX
    Explanations

    code/technical text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ÑĤиÑĢ
    -0.29
    ombine
    -0.28
    æĵį
    -0.27
    -Oct
    -0.27
    oya
    -0.27
    ç§ijåѸ
    -0.26
    è¿ħ
    -0.26
     cient
    -0.26
    GetObject
    -0.25
    ç§ijåѦ
    -0.25
    POSITIVE LOGITS
     hot
    0.31
    olic
    0.31
    hot
    0.30
    .hot
    0.30
    hots
    0.29
    .fromCharCode
    0.28
     Fil
    0.28
     Hot
    0.28
    hol
    0.27
    ner
    0.27
    Activations Density 0.176%

    No Known Activations