© 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. 107924
    Prev
    Next
    INDEX
    Explanations

    Dates/Months

    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
    èĩ¾
    -0.29
    åĬłå¿«å»ºè®¾
    -0.29
     today
    -0.28
     lately
    -0.28
    ä»Ĭ天
    -0.27
     aiding
    -0.27
    ukan
    -0.27
    è¿ijæĹ¥
    -0.27
    mpl
    -0.27
    æĺ¨æĻļ
    -0.27
    POSITIVE LOGITS
    åİŁæĿ¥æĺ¯
    0.29
    æĺ¯æ¯Ķè¾ĥ
    0.28
     suicides
    0.26
    -national
    0.25
    ä¸įåĩºæĿ¥
    0.25
    èĻ½çĦ¶æĺ¯
    0.25
    æĸĹ
    0.24
     sung
    0.24
    ereco
    0.24
    ÙĩÙĬ
    0.24
    Activations Density 4.907%

    No Known Activations