© 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. 97784
    Prev
    Next
    INDEX
    Explanations

    ite

    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
    管çIJĨåĴĮ
    -0.40
    建设åĴĮ
    -0.35
    æĬĢæľ¯åĴĮ
    -0.35
    è´¨éĩıåĴĮ
    -0.34
    ç»ıéªĮåĴĮ
    -0.33
    èĥ½åĬĽåĴĮ
    -0.33
    '&&
    -0.33
    æĸĩåĮĸåĴĮ
    -0.32
    ãģĿãģĹãģ¦
    -0.30
    æŶéĹ´åĴĮ
    -0.29
    POSITIVE LOGITS
    `,
    0.58
    *,
    0.57
    ",
    0.55
    **,
    0.54
    “,
    0.54
    $,
    0.53
    ”,
    0.52
    %,
    0.52
    ',
    0.51
    !,
    0.50
    Activations Density 0.049%

    No Known Activations