© 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. 38251
    Prev
    Next
    INDEX
    Explanations

    numbers followed by period or dollar sign

    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
    AndGet
    -0.09
    acu
    -0.08
     @}
    -0.08
    è¯ģæĺİ书
    -0.08
    _PACKAGE
    -0.08
    åİ¿æķĻèĤ²å±Ģ
    -0.08
    abu
    -0.07
    ÛĮزÛĮ
    -0.07
    çļĦè¿ĺæľī
    -0.07
    urn
    -0.07
    POSITIVE LOGITS
    èIJ½å®ŀ好
    0.06
    è¿ĩ好
    0.06
    _VIS
    0.06
    è¿Ń
    0.06
    好è¿IJ
    0.06
    æī«çłģåħ³æ³¨
    0.06
     functions
    0.06
    sche
    0.06
    æŃ¥æŃ¥é«ĺ
    0.06
    æĤ¯
    0.06
    Activations Density 0.023%

    No Known Activations