© 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. 130766
    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
    rez
    -0.32
    è¶Ĭæĺ¯
    -0.28
    áĥĹ
    -0.27
    ner
    -0.26
     represents
    -0.26
    åŃĺåľ¨çļĦ
    -0.26
     community
    -0.24
    że
    -0.24
    éĢŀ
    -0.24
    masters
    -0.24
    POSITIVE LOGITS
     Cond
    0.28
    é£İçŃĿ
    0.27
    oks
    0.26
    uido
    0.25
    inda
    0.25
    _Dec
    0.24
     MADE
    0.24
    åłĥ
    0.24
     Kar
    0.24
    COPE
    0.24
    Activations Density 35.060%

    No Known Activations

    This feature has no known activations.