© 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. 7410
    Prev
    Next
    INDEX
    Explanations

    units with exponents

    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
    带走
    -0.07
    áb
    -0.07
    踩
    -0.07
    _UDP
    -0.07
    ebin
    -0.06
    pel
    -0.06
    না
    -0.06
    æĪĸåĪłéĻ¤
    -0.06
     Ñģклон
    -0.06
    ä¸Ģ个æĺ¯
    -0.06
    POSITIVE LOGITS
    两çĶ¨
    0.08
    à¸Ļà¹Į
    0.07
    elen
    0.07
    éĩįçļĦ
    0.07
    wise
    0.07
    ständ
    0.07
    ommel
    0.07
    ذاء
    0.06
    âĻª
    0.06
    WARD
    0.06
    Activations Density 0.003%

    No Known Activations