© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 57240
    Prev
    Next
    INDEX
    Explanations

    affirmative or questioning interjections

    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
    并ä¸įçŁ¥éģĵ
    -0.07
    ä»İä½ķ
    -0.07
    vine
    -0.07
    åį´å¾Ī
    -0.07
    åį´æ²¡
    -0.07
    ä½łæĺ¯ä¸įæĺ¯
    -0.07
    å½ĵçĦ¶
    -0.06
    åį´ä¸Ģ缴
    -0.06
    ä½Ĩ并ä¸į
    -0.06
    å½ĵçĦ¶æĺ¯
    -0.06
    POSITIVE LOGITS
    ifiable
    0.08
    ursa
    0.08
    å¸Ĥ人æ°ijæ³ķéĻ¢
    0.08
    ়
    0.07
    WithURL
    0.07
    ably
    0.07
    ilyn
    0.07
    AndGet
    0.07
    chette
    0.07
    leen
    0.07
    Activations Density 0.017%

    No Known Activations