© 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. 22251
    Prev
    Next
    INDEX
    Explanations

    academic journals and publications

    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
    交代
    -0.07
    ç±³é«ĺ
    -0.07
    çijŁçijŁ
    -0.07
     Flush
    -0.07
    室
    -0.07
    opl
    -0.07
    çļĦ羣
    -0.06
     pip
    -0.06
    мене
    -0.06
    å©Ĩå©Ĩ
    -0.06
    POSITIVE LOGITS
    azon
    0.09
    _VOL
    0.08
    æŃ·
    0.08
    á»ķ
    0.08
    _NT
    0.07
    ayet
    0.07
    è¿Ļ个大
    0.07
    ehir
    0.07
    aturated
    0.07
    åİĨ
    0.07
    Activations Density 0.033%

    No Known Activations