© 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. 17679
    Prev
    Next
    INDEX
    Explanations

    IN clause, head position, include file, Panel widget, Lamb waves, scan architecture

    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
    æīĢåľ¨åįķä½į
    -0.07
    iddy
    -0.06
     \"
    -0.06
    vah
    -0.06
     **
    -0.06
    çļĦæīĢæľīä½ľåĵģ
    -0.06
     ÙħØ´
    -0.06
    swer
    -0.06
    æľºä¸Ĭ
    -0.06
    äs
    -0.06
    POSITIVE LOGITS
    çļĦéĩįè¦ģæĢ§åĴĮ
    0.08
    ãĥĩãĤ£ãĥ³ãĤ°
    0.08
    为åķ¥
    0.08
    pager
    0.07
    è·Łèĩªå·±
    0.07
    çŁŃçŁŃ
    0.07
    ạch
    0.07
    æľīåķ¥
    0.07
    lehem
    0.07
    ãĤĴãģĶç´¹ä»ĭ
    0.07
    Activations Density 0.008%

    No Known Activations