© 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. 22-TRANSCODER-HP
    7. 97838
    Prev
    Next
    INDEX
    Explanations

    &

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    个人
    -0.32
    åĪĿ次
    -0.29
    æĸ°çīĪ
    -0.27
    mlink
    -0.26
    ç½¹
    -0.25
    åIJĮæĹ¶ä¹Łæĺ¯
    -0.25
    ç±į
    -0.25
    åIJĮæĹ¶ä¹Ł
    -0.25
    åĩºèº«
    -0.24
    apon
    -0.24
    POSITIVE LOGITS
    presso
    0.26
    -resource
    0.25
     resource
    0.25
    -widgets
    0.25
    orer
    0.25
     field
    0.24
    upy
    0.24
    rÃł
    0.24
    åķĨæĬ¥
    0.24
    éģ¥
    0.24
    Activations Density 0.015%

    No Known Activations