© 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. 64437
    Prev
    Next
    INDEX
    Explanations

    show that if

    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
    ogi
    -0.07
    æĪĸ许æĺ¯
    -0.06
    _TRY
    -0.06
     presumably
    -0.06
    ä»Ĺ
    -0.06
    è¦ģçŁ¥éģĵ
    -0.06
    设æĥ³
    -0.06
    æĥ³çľĭ
    -0.06
    åħ·ä½ĵåĪĨæŀIJ
    -0.06
    笳
    -0.06
    POSITIVE LOGITS
    urgi
    0.09
    æĹłè®ºä»İ
    0.09
    /how
    0.08
    éb
    0.08
    afari
    0.08
    æĹłè®º
    0.07
    overall
    0.07
    åį³ä½¿
    0.07
    æĹłè®ºå¦Ĥä½ķ
    0.07
    åį³ä½¿åľ¨
    0.07
    Activations Density 0.034%

    No Known Activations