© 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. 45678
    Prev
    Next
    INDEX
    Explanations

    explanation

    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
    leman
    -0.08
    æ»¨æ±Ł
    -0.07
    åįļçī©
    -0.07
     pop
    -0.07
    leÅŁ
    -0.07
    秦淮
    -0.07
    à¸Ĭุม
    -0.07
    滨海
    -0.07
    retval
    -0.07
    vaart
    -0.07
    POSITIVE LOGITS
    对è¿ĻäºĽ
    0.06
    aze
    0.06
    éŀŃ
    0.06
    éĢĤåIJĪèĩªå·±
    0.06
    angen
    0.06
    æĥ¹
    0.06
    æĹłæķħ
    0.06
    رب
    0.06
    æ¡
    0.06
    abe
    0.06
    Activations Density 0.002%

    No Known Activations