© 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. 61157
    Prev
    Next
    INDEX
    Explanations

    blue, numbers, LTD, systems

    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
    çļĦè¿ĺæĺ¯
    -0.07
    èĨ³
    -0.07
    äºĨä»Ģä¹Ī
    -0.07
    éķĩ
    -0.07
    said
    -0.07
    éĤ£å°±æĺ¯
    -0.06
    个æĪĸå¤ļ个
    -0.06
    éĤ£ä¹Łæĺ¯
    -0.06
    çļĦéĤ£æł·
    -0.06
    座
    -0.06
    POSITIVE LOGITS
     infatti
    0.10
     إذÙĨ
    0.08
     ugyanis
    0.08
     bowiem
    0.07
     Franç
    0.07
     totiž
    0.07
    ç³»ç»Łä¸İ
    0.07
    (Char
    0.07
    à¹Ģวล
    0.07
     voilÃł
    0.07
    Activations Density 0.002%

    No Known Activations