© 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. 141527
    Prev
    Next
    INDEX
    Explanations

    of

    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
     conceived
    -0.30
    ãģ¾ãģļ
    -0.30
    éŨå¤ĸ
    -0.28
    SEMB
    -0.27
    /process
    -0.27
    ERM
    -0.26
     Skyl
    -0.25
    è¿ĻåĿĹ
    -0.25
     dataGridViewCellStyle
    -0.25
     (£
    -0.24
    POSITIVE LOGITS
     forts
    0.29
    pressions
    0.26
    ug
    0.25
    /html
    0.25
     st
    0.23
    æĺŁ
    0.23
    kj
    0.23
     pand
    0.23
    模仿
    0.23
    ä½ľèĢħæīĢæľī
    0.23
    Activations Density 19.669%

    No Known Activations