© 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. 38465
    Prev
    Next
    INDEX
    Explanations

    non-english characters

    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
    ?(:
    -0.08
    ç»ĵåIJĪåľ¨ä¸Ģèµ·
    -0.07
    licant
    -0.07
    äºĨä¸ĢèĪ¬
    -0.07
    embed
    -0.07
    ({},
    -0.07
    æĹ¶å¯¹
    -0.07
     cim
    -0.07
    æĦļ人
    -0.07
    bid
    -0.07
    POSITIVE LOGITS
    ç¨ĭ
    0.07
    ä¸ĢåĪĻ
    0.06
    èĭij
    0.06
     little
    0.06
    ä¸Ŀä¸Ŀ
    0.06
    æijĺèĩª
    0.06
    ennes
    0.06
    zz
    0.06
    byt
    0.06
    etri
    0.06
    Activations Density 0.096%

    No Known Activations