© 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. 16980
    Prev
    Next
    INDEX
    Explanations

    thing, HD, die, alternatives

    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
    ç³ķ
    -0.07
    ä¸įåIJĮçļĦ人
    -0.07
    è±ģ
    -0.07
    -extra
    -0.07
    常人
    -0.07
    éģ¨
    -0.07
    è¿Ľåĩºåı£ä¿¡çĶ¨
    -0.07
    rippling
    -0.07
    uple
    -0.06
     impi
    -0.06
    POSITIVE LOGITS
    æĽ¿ä»£åĵģ
    0.11
    åıĸ代
    0.10
     alternatives
    0.09
    æĻ®åıĬ
    0.08
    æĽ¿ä»£
    0.08
    æ·ĺæ±°
    0.08
    主æµģ
    0.08
     Absatz
    0.08
    ä¹ĭäºī
    0.08
    äºī夺
    0.08
    Activations Density 0.751%

    No Known Activations