© 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. 129748
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     loophole
    -0.25
    æī®
    -0.24
    çĤ¹çĤ¹å¤´
    -0.24
    itters
    -0.24
     hut
    -0.23
    åĩºåħ¥
    -0.23
    zig
    -0.23
     Gems
    -0.23
    ingo
    -0.23
    ambda
    -0.23
    POSITIVE LOGITS
    æľĿ
    0.31
    åŁİå¢Ļ
    0.29
    conto
    0.28
    conte
    0.28
    ####↵
    0.27
    coe
    0.26
     coerc
    0.26
     ÑģоÑģÑĤо
    0.25
    pras
    0.25
    è¿ĺæĺ¯è¦ģ
    0.25
    Activations Density 6.274%

    No Known Activations

    This feature has no known activations.