© 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. 48916
    Prev
    Next
    INDEX
    Explanations

    d. c. docket nos

    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
    oret
    -0.09
    èĬ³èįī
    -0.07
    çİ°åľ¨å¼Ģå§ĭ
    -0.07
     skr
    -0.07
    iscal
    -0.07
    åİŁæĿ¥æĺ¯
    -0.06
    pred
    -0.06
    isco
    -0.06
    acial
    -0.06
    çĦ¶å¤§
    -0.06
    POSITIVE LOGITS
    dbuf
    0.08
    odat
    0.07
    allery
    0.07
    imar
    0.07
    orra
    0.07
    ÃįN
    0.07
    åľ¨ä¸Ĭè¿°
    0.07
    IMP
    0.06
    çļ±äºĨ
    0.06
    åĬĽè¡Į
    0.06
    Activations Density 0.067%

    No Known Activations