© 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. 63705
    Prev
    Next
    INDEX
    Explanations

    end of clause or code line

    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
    unda
    -0.08
     thus
    -0.08
    è¿Ļæł·å°±åı¯ä»¥
    -0.08
    è¿Ļæł·æĤ¨å°±åı¯ä»¥
    -0.07
    æĦıåij³çĿĢ
    -0.07
    è¿ĻæĦıåij³çĿĢ
    -0.07
    æĦŁè§īå¾Ī
    -0.07
    åIJĪçIJĨ
    -0.06
    oice
    -0.06
     reasonably
    -0.06
    POSITIVE LOGITS
    ä¸Ģåıij
    0.08
    讳
    0.08
    iae
    0.07
    /framework
    0.07
    inson
    0.07
    amanya
    0.07
    æ³ķåĪ¶
    0.07
    ucid
    0.07
     downright
    0.07
    åı£éķĩ
    0.07
    Activations Density 0.002%

    No Known Activations