© 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. 20-TRANSCODER-HP
    7. 108498
    Prev
    Next
    INDEX
    Explanations

    tunnel

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    骨干
    -0.30
     void
    -0.26
    void
    -0.25
     debido
    -0.25
    aina
    -0.25
    é£İ鼨
    -0.25
    ains
    -0.24
     dated
    -0.24
    TextColor
    -0.23
     date
    -0.23
    POSITIVE LOGITS
    ç»ĵ
    0.27
    zeigen
    0.27
    ä¸ĵåįĸ
    0.26
    .dk
    0.26
     ramps
    0.25
    stead
    0.25
    zel
    0.25
    å°±æĥ³
    0.24
    ä¸ĢæĹ¥
    0.24
    onymous
    0.24
    Activations Density 0.838%

    No Known Activations