© 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. 58632
    Prev
    Next
    INDEX
    Explanations

    examples and evidence

    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
    æķħåIJį
    -0.08
    ä¸įæĺ¯æĪij
    -0.07
    ä»İèĢĮ导èĩ´
    -0.07
    ìĤ¬ìĿ¸
    -0.07
    ç¼Ī
    -0.07
     spender
    -0.07
    adier
    -0.07
     ÙĤÙĦت
    -0.06
    丰å¯Įå¤ļ彩çļĦ
    -0.06
    croft
    -0.06
    POSITIVE LOGITS
    åľ¨è¿Ļæĸ¹éĿ¢
    0.11
    è¿Ļæĸ¹éĿ¢çļĦ
    0.10
    对æѤ
    0.09
    解åĨ³è¿Ļ个éĹ®é¢ĺ
    0.09
    çĤºæѤ
    0.08
    ä¸İæѤ
    0.08
    为æѤ
    0.08
    è¿Ļæĸ¹éĿ¢
    0.08
    å°įæѤ
    0.08
    åľ¨è¿Ļç§į
    0.08
    Activations Density 0.588%

    No Known Activations