© 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. 13883
    Prev
    Next
    INDEX
    Explanations

    prudence, time, lords, achieving

    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
    å°¬
    -0.08
    doa
    -0.08
    å°´
    -0.07
    empat
    -0.07
    å¯¹æľ¬æ¬¡
    -0.07
    ceo
    -0.07
    ÃģNG
    -0.07
     frustra
    -0.07
    userinfo
    -0.07
    建模
    -0.07
    POSITIVE LOGITS
     whatever
    0.08
    好好çļĦ
    0.07
    èĥ
    0.07
    åľ¨å¸Ĥåľºä¸Ĭ
    0.07
    身
    0.07
     presumably
    0.07
     ordinary
    0.07
    æĻ®éĢļçļĦ
    0.07
    ä¸įåĸĦ
    0.06
    æīĢèĥ½
    0.06
    Activations Density 0.008%

    No Known Activations