© 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. 64301
    Prev
    Next
    INDEX
    Explanations

    ab

    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
    usher
    -0.28
    agonal
    -0.28
    ines
    -0.24
    ç»Į
    -0.24
     transitions
    -0.24
    Cy
    -0.23
    çļĦåĬ¨ä½ľ
    -0.23
    éĤĵå°ı
    -0.23
     też
    -0.23
    avax
    -0.23
    POSITIVE LOGITS
    æī©å±ķ
    0.25
    é«ĺæ¸ħ
    0.25
     ENC
    0.25
     ÑģмÑĭÑģл
    0.25
    otomy
    0.25
    æľĢåIJİä¸Ģ个
    0.23
    楣
    0.23
    DbContext
    0.23
    itone
    0.23
    æīĺ
    0.23
    Activations Density 1.762%

    No Known Activations