© 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. 107209
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    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
    setLayout
    -0.26
    æĬķæĶ¾
    -0.25
     indefinite
    -0.25
    ãĥŁãĥ¥
    -0.25
    ly
    -0.24
    丼
    -0.24
    åģļåĪ°äºĨ
    -0.24
    ä»»ä½ķå½¢å¼ı
    -0.24
     Refriger
    -0.23
    æĬ½åĩº
    -0.23
    POSITIVE LOGITS
     rects
    0.28
    -guide
    0.26
    大æ´ĭ
    0.26
    indle
    0.25
    æĹ¶ä»£ä¸ŃåĽ½
    0.24
    人å±ħ
    0.24
    èĬĿ
    0.24
    夷
    0.23
    è°´è´£
    0.23
    ched
    0.23
    Activations Density 2.382%

    No Known Activations