© 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. 30-TRANSCODER-HP
    7. 96252
    Prev
    Next
    INDEX
    Explanations

    symbol, symbolic

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     glob
    -0.61
     Glob
    -0.57
    glob
    -0.54
     pattern
    -0.53
     patterns
    -0.49
    Pattern
    -0.48
    pattern
    -0.48
    .glob
    -0.47
    -pattern
    -0.46
     Patterns
    -0.46
    POSITIVE LOGITS
     Symbol
    0.39
    Symbol
    0.35
    symbol
    0.34
     symbolic
    0.34
     symbol
    0.33
     SYMBOL
    0.31
    _symbol
    0.31
    .Symbol
    0.30
    -symbol
    0.30
    符åı·
    0.30
    Activations Density 0.948%

    No Known Activations