© 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. 63200
    Prev
    Next
    INDEX
    Explanations

    Considering/perceiving

    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
    ãģ¨ãģĨ
    -0.27
    cko
    -0.26
    åį°ç«ł
    -0.25
    ocrat
    -0.25
     isNaN
    -0.24
    太è¿ĩ
    -0.24
    icks
    -0.24
    )\<
    -0.24
     Ecology
    -0.24
    -0.23
    POSITIVE LOGITS
    ä»ģ
    0.32
    ANI
    0.28
     winter
    0.27
    @NoArgsConstructor
    0.25
    座
    0.25
    axis
    0.25
     wheel
    0.24
    @brief
    0.24
    brick
    0.24
     modern
    0.24
    Activations Density 10.050%

    No Known Activations