© 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. 3420
    Prev
    Next
    INDEX
    Explanations

    lists directory information

    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
    _foreign
    -0.07
    åľ©
    -0.06
    STYPE
    -0.06
    æ¥Ķ
    -0.06
    åĽºéĨĩ
    -0.06
    à¹Ģà¸Ĥ
    -0.06
    æīĢæĢĿ
    -0.06
    çĤºä½ķ
    -0.06
    ä¸ĸçļĦ
    -0.06
    _gp
    -0.06
    POSITIVE LOGITS
    ä¸Ģè¦ģ
    0.08
    ä¸ĭåĪĹ说æ³ķ
    0.08
    yclopedia
    0.08
    ä¸ĢæĿ¥
    0.07
     encyclopedia
    0.07
     nobody
    0.07
    antan
    0.07
    ATS
    0.07
    æŃ£ç¡®çļĦæĺ¯
    0.07
     banged
    0.07
    Activations Density 0.091%

    No Known Activations