© 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. 130084
    Prev
    Next
    INDEX
    Explanations

    urg

    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
    è·Ł
    -0.25
     Cod
    -0.25
    hap
    -0.24
    æĽ¿æį¢
    -0.24
    irtual
    -0.24
    -ion
    -0.24
    ç«¥
    -0.24
     Equal
    -0.23
    onis
    -0.23
    Equal
    -0.23
    POSITIVE LOGITS
    åĬ¨æľº
    0.28
    levance
    0.27
     underestimated
    0.27
     chóng
    0.27
    otes
    0.26
    æŁIJ个
    0.25
    leta
    0.25
     Keeper
    0.25
     unanimously
    0.25
     DISCLAIMS
    0.24
    Activations Density 1.311%

    No Known Activations