© 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. 17889
    Prev
    Next
    INDEX
    Explanations

    code and special characters

    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
    pei
    -0.30
    ideo
    -0.29
    åĴ¨è¯¢æľįåĬ¡
    -0.27
    åľ¨è¿ĩ渡
    -0.27
    彩èī²
    -0.27
     ostream
    -0.26
    è£Ĵ
    -0.26
    oliday
    -0.26
    acin
    -0.25
    _INTR
    -0.25
    POSITIVE LOGITS
    mith
    0.25
    段
    0.25
     mor
    0.25
    tails
    0.24
     vet
    0.24
     faces
    0.24
    @stop
    0.24
     Financing
    0.24
    ç«ł
    0.24
    edom
    0.23
    Activations Density 1.410%

    No Known Activations