© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 107786
    Prev
    Next
    INDEX
    Explanations

    programming/debugging

    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
    Statements
    -0.25
     trust
    -0.24
     tomorrow
    -0.24
    第ä¸ĢæĿ¡
    -0.24
    answers
    -0.24
     Radio
    -0.24
    MAS
    -0.24
    ught
    -0.24
     nob
    -0.23
    Interior
    -0.23
    POSITIVE LOGITS
    _Invoke
    0.29
    dling
    0.28
    µ¬
    0.27
    iminary
    0.24
    寿
    0.24
    oufl
    0.24
    ully
    0.23
    æĴ
    0.23
    -way
    0.23
    /UI
    0.23
    Activations Density 86.443%

    No Known Activations