© 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. 42172
    Prev
    Next
    INDEX
    Explanations

    action completion or state change

    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
     tackling
    -0.07
    æĪIJ为ä¸Ģ个
    -0.07
    è·³åĩº
    -0.07
    utta
    -0.07
     banged
    -0.07
    urez
    -0.07
    _completion
    -0.07
     banging
    -0.07
    åįĩåĪ°
    -0.07
    马æĸ¯
    -0.06
    POSITIVE LOGITS
    aland
    0.08
     either
    0.07
    iny
    0.07
    该å±Ģ
    0.07
    åİŁä»¶
    0.07
    æľīæĿ¡ä»¶çļĦ
    0.06
    itor
    0.06
    æľīæĿ¡ä»¶
    0.06
    使ä¹ĭ
    0.06
    åĽ¾çīĩæĪĸ
    0.06
    Activations Density 0.412%

    No Known Activations