© 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. 41039
    Prev
    Next
    INDEX
    Explanations

    prime number, odd size, animists

    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
    çļĦä¸ĢåĪĩéĥ½
    -0.11
    俨
    -0.09
    çļĦäººåľ¨
    -0.08
    _PY
    -0.07
    cken
    -0.07
    äºĭæķħçļĦåıijçĶŁ
    -0.07
    缮çŀª
    -0.07
    OLS
    -0.07
    æķĪæŀľåĴĮ
    -0.07
    çĶ«
    -0.07
    POSITIVE LOGITS
    èĢĮä¸Ķæĺ¯
    0.08
    èĢĮä¸įæĺ¯
    0.08
    arro
    0.08
    èĢĮä¸Ķè¿ĺæĺ¯
    0.07
    注æĦıä¼ijæģ¯
    0.06
    èĢĮä¸Ķ
    0.06
    æ°ı
    0.06
    ยà¹Į
    0.06
     ones
    0.06
    èĢĮä¸Ķæľī
    0.06
    Activations Density 0.001%

    No Known Activations