© 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. 46600
    Prev
    Next
    INDEX
    Explanations

    Chinese characters or /of

    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
    人çĶŁä¸Ń
    -0.07
    åİŁä»¶åıĬ
    -0.07
    ------------------------------
    -0.07
    åħ¢åħ¢
    -0.07
    ç»ıæµİçļĦåıijå±ķ
    -0.06
    åı¯ä¸į
    -0.06
    çĻĸ
    -0.06
    绪
    -0.06
    itarios
    -0.06
    تÙĬ
    -0.06
    POSITIVE LOGITS
    å®īåħ¨ç¬¬ä¸Ģ
    0.07
    æīĢå±ŀåĪĨç±»
    0.07
    é¢ĩå¤ļ
    0.07
    é§ħå¾ĴæŃ©
    0.07
    çĪ±ä¸į
    0.07
    èµĦæºIJåħ±äº«
    0.07
    /of
    0.07
    çļĨæľī
    0.07
    ä¾Ŀæ³ķæ²»
    0.06
    é¦Ĩ
    0.06
    Activations Density 0.063%

    No Known Activations