© 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. 63655
    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
    åħ¥åħļ
    -0.27
    æľ¬ç«Ļ
    -0.26
    iggers
    -0.26
    ä¸īæľŁ
    -0.26
    å¥ĩ
    -0.26
    æľ¬ç½ij
    -0.25
    äºĮæľŁ
    -0.24
    离
    -0.24
    SITE
    -0.24
    å¿Ĺ
    -0.23
    POSITIVE LOGITS
     vs
    0.28
     Hobby
    0.28
     =&
    0.28
    –and
    0.26
    åıªæĺ¯
    0.26
    æĺ¯æľĢ好çļĦ
    0.26
    åľī
    0.25
    çī¡
    0.25
    pty
    0.25
    :pk
    0.25
    Activations Density 3.405%

    No Known Activations

    This feature has no known activations.