© 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. 48821
    Prev
    Next
    INDEX
    Explanations

    numbers ending in 00 or 5

    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
    ×Ŀ
    -0.08
    çľĭ
    -0.07
    dued
    -0.07
    éĿĴæ¢ħ
    -0.06
    ף
    -0.06
    İ
    -0.06
    èĭ¥ä¸įæĺ¯
    -0.06
    ilea
    -0.06
    éĿĻ
    -0.06
    ãĥ³ãģ®
    -0.06
    POSITIVE LOGITS
    0.08
    ÂŃ
    0.08
    âĢij
    0.08
    \_
    0.08
     <![
    0.08
    çļĦåij¢
    0.07
    âĢIJ
    0.07
    ä¹ĭ以
    0.07
    bstract
    0.07
    ä¹ĭæĺŁ
    0.07
    Activations Density 0.018%

    No Known Activations