© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 38916
    Prev
    Next
    INDEX
    Explanations

    my hero academia

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĨ²
    -0.07
    é¾
    -0.07
    æª
    -0.06
    åĩºèĩª
    -0.06
    еÑģÑĮ
    -0.06
    è´«
    -0.06
    宾
    -0.06
    .Pool
    -0.06
    é½
    -0.06
    ür
    -0.06
    POSITIVE LOGITS
    Õ¡Õ£
    0.09
    è¿ĻåĿĹ
    0.08
    pum
    0.07
    éĩijåŃĹå¡Ķ
    0.07
    berg
    0.07
    pedia
    0.07
    ưỡng
    0.07
    ä¸įåı¯æĢĿè®®
    0.07
    çŁ¥éģĵæĪij
    0.07
    çĽ¸ä¼ł
    0.07
    Activations Density 0.278%

    No Known Activations