© 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. 29197
    Prev
    Next
    INDEX
    Explanations

    correctness and definitions

    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
    å¾ģå¾Ĺ
    -0.08
    alog
    -0.08
    alice
    -0.08
     оÑĤм
    -0.07
    лÑij
    -0.07
    æµij
    -0.07
     @_
    -0.07
     ube
    -0.07
    prud
    -0.07
    oot
    -0.07
    POSITIVE LOGITS
    æĮīçIJĨ
    0.15
     pourtant
    0.11
    ä¸įåºĶ该
    0.11
    ãģ¯ãģļ
    0.11
    æĢİä¹Īä¼ļ
    0.10
    æĢİä¹Īåı¯èĥ½
    0.09
    æĺİæĺİ
    0.09
    éļ¾éģĵ
    0.09
     shouldn
    0.09
    ä¸į该
    0.08
    Activations Density 0.159%

    No Known Activations