© 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. 21165
    Prev
    Next
    INDEX
    Explanations

    philanthropic summit, radio items, content investment, selenium upload, neuropathy, blogging career, monastery brewing, inflammatory diseases, divorce assets

    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
    oub
    -0.08
    ä¸įå½Ĵ
    -0.08
    á»Ļc
    -0.08
    íģIJ
    -0.08
    institut
    -0.07
    ×ĵת
    -0.07
    cules
    -0.07
     Playback
    -0.07
    vou
    -0.07
    çģ¯çģ«
    -0.07
    POSITIVE LOGITS
    arder
    0.07
     monet
    0.07
    æĬĬéĴ±
    0.07
    溢
    0.07
     indemn
    0.07
     ROI
    0.07
     usufr
    0.07
    ä¼°ç®Ĺ
    0.07
    çļĦèĥ½éĩı
    0.07
    èĢĹ
    0.07
    Activations Density 0.560%

    No Known Activations