© 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. 56253
    Prev
    Next
    INDEX
    Explanations

    in many cases

    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
     accordingly
    -0.07
    å½ĵä¸ĭ
    -0.07
    ÐijÐļ
    -0.06
    itari
    -0.06
    rier
    -0.06
    enus
    -0.06
    å½ĵä¸ĭçļĦ
    -0.06
    å°ıå·§
    -0.06
    éĢļ常æĥħåĨµä¸ĭ
    -0.06
     famously
    -0.06
    POSITIVE LOGITS
    akan
    0.07
    ëģĶ
    0.07
    -aut
    0.07
    inten
    0.07
    erweise
    0.07
    ppure
    0.07
    indow
    0.07
    zte
    0.06
    æľ¬æ¥¼
    0.06
    俱ä¹IJéĥ¨
    0.06
    Activations Density 0.260%

    No Known Activations