© 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. 17302
    Prev
    Next
    INDEX
    Explanations

    struggling or fumbling actions

    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
    äºĮè¯Ŀ
    -0.10
    ä¸Ģåİ»
    -0.08
    _strike
    -0.08
    Targets
    -0.08
    æĹłéľĢ
    -0.07
    füh
    -0.07
    ิริ
    -0.07
    indow
    -0.07
    å½ĵ头
    -0.07
    åĪĥ
    -0.07
    POSITIVE LOGITS
    æĮ£æīİ
    0.10
     unsuccessfully
    0.09
    ãģªãģĮãĤīãĤĤ
    0.09
     desperately
    0.09
    èī°éļ¾çļĦ
    0.09
     ëģĿìĹIJ
    0.09
    åĭī强
    0.09
    çĿĢæĥ³
    0.08
    ps
    0.08
    عث
    0.08
    Activations Density 0.177%

    No Known Activations