© 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. 26416
    Prev
    Next
    INDEX
    Explanations

    names ending in "mond", "ory", "arry", "ryan", "ard", "erry", "eroy", "ordon", "isco"

    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
     Ayd
    -0.07
    -controls
    -0.07
    ç²¾è¯ļ
    -0.07
    åĬªåĬĽåģļåĪ°
    -0.07
     Raq
    -0.07
     scare
    -0.07
    اÛĮت
    -0.07
    zelt
    -0.07
    èIJ¨æĸ¯
    -0.06
    ä¸ĭå®ļ
    -0.06
    POSITIVE LOGITS
     de
    0.08
    å¦ĤæŀľæĤ¨å¯¹
    0.08
    BuilderFactory
    0.08
    etta
    0.07
     ÐĺвановиÑĩ
    0.07
     van
    0.07
    ORED
    0.07
    æľ¬æł¼
    0.07
    ette
    0.07
    áĢ·
    0.06
    Activations Density 0.986%

    No Known Activations