© 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. 41283
    Prev
    Next
    INDEX
    Explanations

    question openers and punctuation

    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
    对ä¸Ĭè¿°
    -0.07
    æĮijæĪĺæĢ§
    -0.07
    ç»Ħç»ĩ建设
    -0.07
    åľ¨ä¸Ĭè¿°
    -0.07
    çªģè¢Ń
    -0.06
    åĩłåĪĨ
    -0.06
    :num
    -0.06
    ĥĿ
    -0.06
    ÏĮ
    -0.06
    æĪijåıªå¥½
    -0.06
    POSITIVE LOGITS
    arana
    0.08
    aira
    0.08
    FTA
    0.08
     "...
    0.08
    éĹĬ
    0.07
    <|im_start|>
    0.07
    奮
    0.07
    åªĽ
    0.07
    orit
    0.07
     صÙĪت
    0.07
    Activations Density 0.670%

    No Known Activations