© 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. 51408
    Prev
    Next
    INDEX
    Explanations

    circuitry and components

    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
    ock
    -0.08
    è´«
    -0.07
    éĩĩ
    -0.07
    浩
    -0.07
    åľ¨éĩĮéĿ¢
    -0.07
    kab
    -0.07
    å±ŀåľ°
    -0.07
    اÙĦا
    -0.06
    ulu
    -0.06
    åİŁå§ĭçļĦ
    -0.06
    POSITIVE LOGITS
    æĸ°åĬłåĿ¡
    0.08
    é¡ı
    0.08
    ircuit
    0.07
    à¥Ĥप
    0.07
    _sep
    0.07
    ÙħÙĬÙħ
    0.07
    æŀ¶æŀĦ
    0.07
    çļĦ设计é£İæł¼
    0.07
    ator
    0.07
    _SEPARATOR
    0.07
    Activations Density 0.292%

    No Known Activations