© 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. 14520
    Prev
    Next
    INDEX
    Explanations

    may not be the case

    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
    arau
    -0.09
     شبÙĩ
    -0.09
    大æ¦Ĥæĺ¯
    -0.09
    èĩ³å°ijåľ¨
    -0.09
    Ùĥات
    -0.08
     kaut
    -0.08
    å¤§çº¦åľ¨
    -0.08
    kira
    -0.08
    大约æĺ¯
    -0.08
    大ç´Ħ
    -0.08
    POSITIVE LOGITS
    æľªå¿ħ
    0.16
    ä¸įä¸Ģå®ļ
    0.15
    ä¹Łä¸įä¸Ģå®ļ
    0.13
    ä¸įä¸Ģå®ļæĺ¯
    0.12
    ä¹Łåı¯èĥ½
    0.11
    ä¹Łæľªå¿ħ
    0.10
     may
    0.10
     depending
    0.09
    ãģ«ãĤĪãģ£ãģ¦ãģ¯
    0.09
     sometimes
    0.09
    Activations Density 0.084%

    No Known Activations