© 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. 141207
    Prev
    Next
    INDEX
    Explanations

    Selection, choice, decision

    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
    chains
    -0.27
    łéĻ¤
    -0.26
    tes
    -0.26
    ËĬ
    -0.26
     Chase
    -0.26
    mente
    -0.25
    -digit
    -0.24
    ç¥
    -0.24
     beyond
    -0.24
    eten
    -0.24
    POSITIVE LOGITS
    (sw
    0.26
    ä¼ĺ
    0.25
    æľīæĦıä¹ī
    0.25
    ampp
    0.25
    amax
    0.24
    %";↵
    0.24
    æºŁ
    0.24
    ynos
    0.23
    fail
    0.23
    ä¼ĺéĢī
    0.23
    Activations Density 10.840%

    No Known Activations