© 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. 32715
    Prev
    Next
    INDEX
    Explanations

    user interface actions

    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
    ilmington
    -0.07
     سرا
    -0.07
    èī¯
    -0.07
    éĢĤå½ĵ
    -0.07
    åı¯ä»¥éĢĤå½ĵ
    -0.06
    çļĦçľ¼ç¥ŀ
    -0.06
    åı¯éĢĤå½ĵ
    -0.06
    à¸ŀย
    -0.06
    iq
    -0.06
     Arg
    -0.06
    POSITIVE LOGITS
     inputs
    0.09
    ved
    0.08
     input
    0.08
    è¾ĵåħ¥
    0.08
     clicked
    0.08
     interac
    0.08
     triggering
    0.07
    è¾ĵåħ¥çļĦ
    0.07
    _TRIGGER
    0.07
    触åıij
    0.07
    Activations Density 0.763%

    No Known Activations