© 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. 45081
    Prev
    Next
    INDEX
    Explanations

    conduction system pathways bundle branch

    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
    çī©
    -0.07
    轻轻æĿ¾
    -0.07
    å¾ģæ±Ĥ
    -0.07
     scaling
    -0.07
    errat
    -0.07
    éĽĨä¸Ńæķ´æ²»
    -0.07
    åľ¨å½ĵåľ°
    -0.07
    æIJ¬è¿ģ
    -0.07
     worldview
    -0.07
    è¿ĶåĽŀåĪĹ表
    -0.07
    POSITIVE LOGITS
    æ¯ıç§Ĵ
    0.08
    åħĪéĶĭéĺŁ
    0.07
    æ¯ıåĪĨéĴŁ
    0.07
    ä¼łå¯¼
    0.07
    arella
    0.07
     orderly
    0.07
    èµ°å¾Ĺ
    0.07
     spread
    0.07
     syn
    0.07
     sync
    0.07
    Activations Density 0.033%

    No Known Activations