© 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. 9475
    Prev
    Next
    INDEX
    Explanations

    whether questions

    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
    á»ī
    -0.07
    ä»Ģä¹Īåij¢
    -0.07
    æķĻå¸Īè¦ģ
    -0.07
     harap
    -0.07
    è¦ģä¸įè¦ģ
    -0.07
    è¦ģä¿Ŀè¯ģ
    -0.07
     Hopefully
    -0.07
     afer
    -0.07
    à¸ļรร
    -0.06
    exter
    -0.06
    POSITIVE LOGITS
    æĿ¥å¾ĹåıĬ
    0.10
    æľīä»»ä½ķ
    0.10
    akah
    0.09
     somehow
    0.09
    оеди
    0.08
    è¿ĺæľīåħ¶ä»ĸ
    0.08
    符åIJĪ
    0.08
    veyor
    0.08
    éģĹæ¼ı
    0.08
     alguno
    0.08
    Activations Density 0.019%

    No Known Activations