© 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. 27349
    Prev
    Next
    INDEX
    Explanations

    writing tutorials, blog posts, or documentation

    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
    为çĶ±
    -0.07
    åħ¶ä¸Ńæľī
    -0.06
    levance
    -0.06
    à¹Ģà¸Ķียวà¸ģัà¸ļ
    -0.06
    åĪ°åħ¶ä»ĸ
    -0.06
    å¸Īå§IJ
    -0.06
    elon
    -0.06
    çļĦæĦıæĢĿæĺ¯
    -0.06
    ero
    -0.06
    ä¸Ģçľĭ
    -0.06
    POSITIVE LOGITS
    åıĬåĪ©æģ¯
    0.08
    请ç¨įåĢĻ
    0.07
    ourt
    0.07
    _ib
    0.07
    å°Ķåħĭ
    0.07
    åŃIJäºĨ
    0.07
    ówek
    0.07
    éĴ±äºĨ
    0.07
    Ò·
    0.07
    quential
    0.07
    Activations Density 0.003%

    No Known Activations