© 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. 17805
    Prev
    Next
    INDEX
    Explanations

    foreign languages/names

    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
     Fam
    -0.32
    ppo
    -0.31
    lington
    -0.26
    éĥ¨
    -0.25
    ptime
    -0.25
    FK
    -0.25
    losures
    -0.25
    lename
    -0.25
     Fun
    -0.24
    dojo
    -0.24
    POSITIVE LOGITS
    SEG
    0.29
    inters
    0.27
    .sax
    0.27
    è¡Ĺ
    0.25
    人次
    0.25
    ç»İ
    0.24
     SEG
    0.23
    metrics
    0.23
    ont
    0.23
    daf
    0.23
    Activations Density 2.610%

    No Known Activations