© 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. 18911
    Prev
    Next
    INDEX
    Explanations

    question words 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
    /
    -0.07
    åŀ£
    -0.07
    ↵
    -0.06
    ç¼ł
    -0.06
    -0.06
    轩
    -0.06
    **
    -0.06
    (
    -0.05
    ç»ı
    -0.05
    éĻĮ
    -0.05
    POSITIVE LOGITS
    <|box_end|>
    0.09
    adar
    0.09
    åĽ¢åĽ¢
    0.09
    ิà¹īà¸Ļ
    0.09
    ä¹ĭ梦
    0.09
    产åĵģåĪĨç±»
    0.09
    ä¼ļ使çĶ¨
    0.08
    chow
    0.08
    ĵĴ
    0.08
    startswith
    0.08
    Activations Density 0.028%

    No Known Activations