© 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. 1435
    Prev
    Next
    INDEX
    Explanations

    number of carbon atoms

    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
    äºĶ彩
    -0.07
    lei
    -0.07
    äºĭåħ³
    -0.07
    ä¹ĭä¸į
    -0.06
    æ¯ıå¹³æĸ¹ç±³
    -0.06
    ible
    -0.06
    æī°åĬ¨
    -0.06
    妥
    -0.06
    ÙĪار
    -0.06
    翻天
    -0.06
    POSITIVE LOGITS
     Connectivity
    0.09
    /connect
    0.09
     connectivity
    0.09
    éĵ¾
    0.08
     numel
    0.08
    缸è¿ŀ
    0.07
    [Byte
    0.07
    ç¼ĸåı·
    0.07
    loan
    0.07
    çļĦä¸Ģ家
    0.07
    Activations Density 0.006%

    No Known Activations