© 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. 18344
    Prev
    Next
    INDEX
    Explanations

    parenthetical clause end

    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
     mon
    -0.07
     maj
    -0.06
    æĺ¯ä»Ģä¹Īåij¢
    -0.06
    ç³»çļĦ
    -0.06
     Tren
    -0.06
     })).
    -0.06
    è¿Ļæĺ¯å¯¹
    -0.06
     Mes
    -0.06
     (
    -0.06
    æľĪåŃIJ
    -0.06
    POSITIVE LOGITS
    emer
    0.09
    æĨ¬
    0.08
    urette
    0.08
    çĮľä½łåĸľæ¬¢
    0.08
    erber
    0.08
    çĴ¨
    0.08
    odel
    0.08
    çĶ¨çģ«
    0.08
    uret
    0.08
    лÑĥм
    0.08
    Activations Density 0.181%

    No Known Activations