© 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. 61057
    Prev
    Next
    INDEX
    Explanations

    code syntax and structure

    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
    æĺ¥åįİ
    -0.08
    æĿIJæĸĻåıĬ
    -0.07
     op
    -0.07
     Palm
    -0.07
     "*"
    -0.07
    etchup
    -0.07
     Op
    -0.06
    å¸ľ
    -0.06
    artner
    -0.06
    æ¡©
    -0.06
    POSITIVE LOGITS
    SSIP
    0.08
    æľ¬ç«Ļ
    0.08
     Tro
    0.07
    _FMT
    0.07
    ียà¸ļ
    0.07
    yms
    0.07
    ä¸ĢåĪĩéĥ½æĺ¯
    0.07
    äne
    0.07
    ideal
    0.07
     licha
    0.07
    Activations Density 0.069%

    No Known Activations