© 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. 108042
    Prev
    Next
    INDEX
    Explanations

    scientific texts

    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
    udem
    -0.25
    å·¥ä¸ļä¼ģä¸ļ
    -0.24
     gam
    -0.24
     rational
    -0.24
     formally
    -0.23
     being
    -0.23
     UD
    -0.23
     Flam
    -0.23
     visible
    -0.23
     exhausted
    -0.23
    POSITIVE LOGITS
    onChange
    0.27
    terior
    0.26
    ystick
    0.26
     Patty
    0.25
    以åīį
    0.25
    tti
    0.24
    åIJ¯
    0.24
    å±ı
    0.24
     Shane
    0.24
    è¿Ļæĸ¹éĿ¢
    0.24
    Activations Density 3.269%

    No Known Activations