© 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. 129874
    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
    merican
    -0.27
    yne
    -0.27
    åIJĮæĹ¶ä¹Łæĺ¯
    -0.26
    éĢĢåĩº
    -0.26
    åĩºçĶŁ
    -0.26
    æ°ijçĶ¨
    -0.25
    (($
    -0.25
    æ¿ij
    -0.24
    ä»ĭåħ¥
    -0.24
    styles
    -0.23
    POSITIVE LOGITS
    ICC
    0.26
    еÑĤÑĮ
    0.26
    åįķ身
    0.26
    æīįçŁ¥éģĵ
    0.25
    æĢģ
    0.25
    enance
    0.25
    èĢĥ
    0.24
     entertain
    0.24
     menn
    0.24
    个æľĪåĨħ
    0.24
    Activations Density 28.591%

    No Known Activations

    This feature has no known activations.