© 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. 39518
    Prev
    Next
    INDEX
    Explanations

    number dividing and grouping

    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
    çļĻ
    -0.07
    çĴ
    -0.07
    åı¯ä»¥è¯´
    -0.07
    LocalizedString
    -0.06
     suspended
    -0.06
    capitalize
    -0.06
    å¹´åĪĿ
    -0.06
    ä¸Ń西åĮ»
    -0.06
     Amend
    -0.06
    åĵĦ
    -0.06
    POSITIVE LOGITS
    åĪĨæĪIJ
    0.11
    åĪĨç»Ħ
    0.10
    åĪĴåĪĨ为
    0.09
    æĺ¯æĮī
    0.09
    æĮī
    0.09
    并æĮī
    0.09
     grouping
    0.09
     divis
    0.09
    åı¯æĮī
    0.09
     divid
    0.08
    Activations Density 0.039%

    No Known Activations