© 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. 58415
    Prev
    Next
    INDEX
    Explanations

    consecutive options without lock

    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
    å°Ķé¡¿
    -0.09
    åIJĦé¡¹å·¥ä½ľçļĦ
    -0.08
    à¸ĵà¹Į
    -0.08
    ughs
    -0.07
    odox
    -0.07
    estig
    -0.07
    íĶĦëĿ¼
    -0.07
    大è¯Ŀ
    -0.07
     lép
    -0.07
    åĭ¾
    -0.07
    POSITIVE LOGITS
    æĹ¢çĦ¶
    0.07
    å¤ļå¾Ĺ
    0.07
    à¸Īุ
    0.07
    èĤ¯å®ļè¦ģ
    0.07
    çļĦç¡®
    0.07
    ++
    0.06
    wp
    0.06
     unless
    0.06
    éĿł
    0.06
    ru
    0.06
    Activations Density 0.007%

    No Known Activations