© 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. 64322
    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
    $ar
    -0.24
    端
    -0.24
     volt
    -0.24
    legate
    -0.24
    itest
    -0.24
    è´·
    -0.23
    aly
    -0.23
    éļIJ身
    -0.23
    æ¯ħ
    -0.23
    (';
    -0.23
    POSITIVE LOGITS
    Breaking
    0.28
    人æ°Ķ
    0.27
    gings
    0.26
     breaking
    0.26
     Breaking
    0.26
    Break
    0.25
     contiguous
    0.25
    enter
    0.24
    åĽ½åĬ¡
    0.24
    没åħ³ç³»
    0.24
    Activations Density 5.670%

    No Known Activations

    This feature has no known activations.