© 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. 55560
    Prev
    Next
    INDEX
    Explanations

    contribution or help

    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
    æ·±åıĹ广大
    -0.07
     tactic
    -0.07
    æµģè¿ŀ
    -0.06
    æIJĶ
    -0.06
    åĩł
    -0.06
    ÑħÑĸд
    -0.06
    让人
    -0.06
    ç»Ļ人çļĦ
    -0.06
    eline
    -0.06
    Complex
    -0.06
    POSITIVE LOGITS
    è´¡çĮ®
    0.16
     contribute
    0.14
     contributions
    0.14
    åıĤä¸İåĪ°
    0.14
     contributing
    0.14
     contribu
    0.14
     contribution
    0.14
    è²¢çį»
    0.13
     contributes
    0.13
    contrib
    0.13
    Activations Density 0.263%

    No Known Activations