© 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. 51235
    Prev
    Next
    INDEX
    Explanations

    each/all quantifier

    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
    å¤ļ家
    -0.07
    ospace
    -0.07
     calendars
    -0.07
     Others
    -0.06
    apan
    -0.06
    ç¡®æľī
    -0.06
    oes
    -0.06
    å¤ļ人
    -0.06
    æ¯ı人
    -0.06
    fung
    -0.06
    POSITIVE LOGITS
     egyes
    0.09
     constituent
    0.09
    ç»ĦæĪIJéĥ¨åĪĨ
    0.08
     einzelnen
    0.08
     components
    0.08
    ç±³ç²Ĵ
    0.08
     COMPONENT
    0.08
     componente
    0.08
     pixels
    0.08
     jednotliv
    0.08
    Activations Density 0.178%

    No Known Activations