© 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. 63803
    Prev
    Next
    INDEX
    Explanations

    informational questions and answers

    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
    æĦŁåħ´è¶£
    -0.31
    credit
    -0.26
     interest
    -0.26
    appen
    -0.26
     credit
    -0.26
    cred
    -0.25
    æĦŁåħ´è¶£çļĦ
    -0.25
    ref
    -0.24
    åĬª
    -0.24
     ch
    -0.24
    POSITIVE LOGITS
    ollo
    0.33
     maur
    0.29
    éĺľ
    0.29
     Compared
    0.27
    åģļ强
    0.27
    æ³Ľ
    0.27
    é¾Ļ头
    0.26
    ermann
    0.26
    ducted
    0.25
     Derrick
    0.24
    Activations Density 7.378%

    No Known Activations