© 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. 32885
    Prev
    Next
    INDEX
    Explanations

    mathematical induction proof

    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
    itter
    -0.07
    缸éļı
    -0.07
    ines
    -0.07
     impl
    -0.06
    wehr
    -0.06
    ä¸įåı¯éģ¿åħįåľ°
    -0.06
    å¼łæµ·
    -0.06
    Imp
    -0.06
    VIC
    -0.06
    å¿ħ究
    -0.06
    POSITIVE LOGITS
     astonished
    0.07
    纾
    0.07
    çĽ¡
    0.07
    æīĢå±ŀåĪĨç±»
    0.07
    åıijå±ķä¸Ńå¿ĥ
    0.07
    ASON
    0.07
    ä¸įè§ī
    0.06
    缸è¾ħ缸æĪIJ
    0.06
    åĴĮ第
    0.06
    xDB
    0.06
    Activations Density 0.213%

    No Known Activations