© 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. 64022
    Prev
    Next
    INDEX
    Explanations

    Prices and numerical data

    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
    uhe
    -0.28
    /as
    -0.26
    schlie
    -0.25
    æ¾į
    -0.25
    rne
    -0.24
     Us
    -0.23
    å¥ķ
    -0.23
     windows
    -0.23
     sak
    -0.23
     Colt
    -0.23
    POSITIVE LOGITS
    æĢ§åĴĮ
    0.28
     Pause
    0.25
    ality
    0.25
    ä¾Ŀæ³ķ追究
    0.25
    arity
    0.25
    arest
    0.25
    毫æĹł
    0.25
    Ø·ÙĨ
    0.25
    Pause
    0.24
    éĿĻ
    0.24
    Activations Density 2.341%

    No Known Activations