© 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. 43874
    Prev
    Next
    INDEX
    Explanations

    code definitions and syntax

    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
    izio
    -0.08
    igli
    -0.07
    为ä»ĸ人
    -0.07
    ahun
    -0.07
    ieri
    -0.07
    itz
    -0.07
    iria
    -0.07
    anni
    -0.07
    æ·µ
    -0.07
    èIJ¥éĢłèī¯å¥½çļĦ
    -0.06
    POSITIVE LOGITS
    çĽĺçļĦ
    0.07
    enor
    0.07
    æĽ´çĶŁ
    0.07
    lator
    0.07
    мееÑĤÑģÑı
    0.07
    eggi
    0.07
    缤
    0.06
    ensibly
    0.06
    à¸Ļำมา
    0.06
    大å¸Ŀ
    0.06
    Activations Density 0.002%

    No Known Activations