© 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. 26816
    Prev
    Next
    INDEX
    Explanations

    existence of certain words

    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
    ç¼ĵ
    -0.11
    ortable
    -0.09
    ilot
    -0.08
    auta
    -0.08
    æĽ´ä¸įæĺ¯
    -0.08
    кнÑĥ
    -0.08
     RequestOptions
    -0.08
    auge
    -0.07
    ambe
    -0.07
    plevel
    -0.07
    POSITIVE LOGITS
    æĦıåij³çĿĢ
    0.07
    é¦ĸåħĪéľĢè¦ģ
    0.07
    çļĦåŁºæľ¬è¦ģæ±Ĥ
    0.07
    设计è¦ģæ±Ĥ
    0.07
    æ¯ı天éĥ½ä¼ļ
    0.06
    æ¯ıå¹´éĥ½ä¼ļ
    0.06
    igh
    0.06
    éĬĺ
    0.06
    i
    0.06
    è¿ĻæĦıåij³çĿĢ
    0.06
    Activations Density 0.012%

    No Known Activations