© 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. 1252
    Prev
    Next
    INDEX
    Explanations

    bullet points or lists

    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
    anic
    -0.09
    uzzi
    -0.08
    ulich
    -0.08
    ingly
    -0.07
    éĥijéĩį声æĺİ
    -0.07
    ä¹ŁæĽ´
    -0.07
    /ac
    -0.07
    ÑģÑģен
    -0.07
     ensuing
    -0.07
    ä¹Łå¾Īæľī
    -0.07
    POSITIVE LOGITS
     âľĶ
    0.07
    çļĦ大äºĭ
    0.07
    åıĪ称
    0.06
     -
    0.06
    éĢļè¿ĩåIJİ
    0.06
    è¨Ĭ
    0.06
    ä¼ĹæīĢåij¨çŁ¥
    0.06
    ADATA
    0.06
    è®°èĢħåľ¨
    0.06
    尼奥
    0.06
    Activations Density 0.027%

    No Known Activations