© 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. 130755
    Prev
    Next
    INDEX
    Explanations

    computer science and programming

    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
    ç¦ıåĪ©
    -0.27
    ikan
    -0.26
    inished
    -0.26
    avanaugh
    -0.25
    -pound
    -0.24
     Tecn
    -0.24
    bil
    -0.24
     Constit
    -0.24
    /stdc
    -0.24
     Cast
    -0.24
    POSITIVE LOGITS
    itia
    0.28
    ätt
    0.25
    ders
    0.24
     ÑģооÑĤвеÑĤ
    0.24
    éĬĢ
    0.24
    éĵĻ
    0.24
    cca
    0.24
    ä½łä¼ļ
    0.24
    RAP
    0.24
     gehört
    0.23
    Activations Density 14.468%

    No Known Activations