© 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. 27152
    Prev
    Next
    INDEX
    Explanations

    normal states or values

    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
    åŃ
    -0.09
    enheim
    -0.08
    ĥĿ
    -0.08
    ừa
    -0.07
    æºĸ
    -0.07
    edad
    -0.07
    elleen
    -0.07
    åĩĨ
    -0.07
    parcel
    -0.07
    èݽ
    -0.07
    POSITIVE LOGITS
    æŃ£å¸¸æĥħåĨµä¸ĭ
    0.14
     expected
    0.12
    çļĦæŃ£å¸¸
    0.12
    ä¸įåºĶ该
    0.12
    æŃ£å¸¸
    0.12
    æŃ£å¸¸çļĦ
    0.12
    åºĶ该æľī
    0.11
    æĺ¯æŃ£å¸¸çļĦ
    0.11
    åºĶæľīçļĦ
    0.11
    åºĶæľī
    0.11
    Activations Density 0.065%

    No Known Activations