© 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. 4539
    Prev
    Next
    INDEX
    Explanations

    chapter and verse numbers

    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
    ä½°
    -0.08
    å¡
    -0.07
    éĢ
    -0.07
    æ³ĵ
    -0.07
    TER
    -0.07
    pah
    -0.07
    ujuk
    -0.07
    باع
    -0.07
    terminated
    -0.06
     \/
    -0.06
    POSITIVE LOGITS
    batis
    0.08
    è·¯ç«Ļ
    0.07
    åĨįè§ģ
    0.07
    ä»ĸåıª
    0.06
    çļĦéĩįçĤ¹
    0.06
    ç§ijæĬĢé¦Ĩ
    0.06
    raits
    0.06
     Ùħبار
    0.06
    ='.
    0.06
    åħ¨åĬĽåģļ好
    0.06
    Activations Density 0.239%

    No Known Activations