© 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. 3836
    Prev
    Next
    INDEX
    Explanations

    Superintendent

    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
    olle
    -0.09
    ales
    -0.08
    gni
    -0.08
    wez
    -0.08
    hein
    -0.07
    osten
    -0.07
    ÑĢеменно
    -0.07
    æĸ¤
    -0.07
    çł´æµª
    -0.07
    olini
    -0.07
    POSITIVE LOGITS
    ‘
    0.06
    ä¸Ģé½IJ
    0.06
    avor
    0.06
    ç¥Ŀ
    0.06
    ä¸įçŁ¥ä¸įè§ī
    0.05
    rites
    0.05
    ä¸ĢæĶ¯
    0.05
     tweaked
    0.05
     Consort
    0.05
    ä¸ĢæĻļ
    0.05
    Activations Density 0.004%

    No Known Activations