© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 16918
    Prev
    Next
    INDEX
    Explanations

    equals or greater than

    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
    lac
    -0.07
    strup
    -0.07
    åħĨ
    -0.07
    ompok
    -0.07
    çŁ¥
    -0.07
     Roos
    -0.07
     itulah
    -0.07
    鬼
    -0.07
    æĹħ游度åģĩåĮº
    -0.07
    æĪij们è¿ĺæĺ¯
    -0.06
    POSITIVE LOGITS
    åĩ¡
    0.08
    æĺ¯ä¸ĢåĪĩ
    0.07
    æĺ
    0.07
    å°ij
    0.06
    ืà¸Ńà¸Ļ
    0.06
    seiten
    0.06
    quals
    0.06
    Been
    0.06
    èij
    0.06
    å°ıéģĵ
    0.06
    Activations Density 0.042%

    No Known Activations