© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30130
    Prev
    Next
    INDEX
    Explanations

    bottom

    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
     доÑĢого
    -0.09
    é«ĺä»·
    -0.08
    çĪ±æĥľ
    -0.08
    bauer
    -0.08
    ä¸Ĭ游
    -0.08
    ielli
    -0.08
    awe
    -0.08
    rom
    -0.07
    %%%
    -0.07
     fuga
    -0.07
    POSITIVE LOGITS
     bottom
    0.15
     Bottom
    0.14
    (bottom
    0.14
    bottom
    0.14
     below
    0.14
    Bottom
    0.13
    æĽ´ä½İ
    0.13
    åľ¨ä¸ĭéĿ¢
    0.12
    below
    0.12
    ลà¹Īาà¸ĩ
    0.12
    Activations Density 0.239%

    No Known Activations