© 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. 49541
    Prev
    Next
    INDEX
    Explanations

    publications and research papers

    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
    ntag
    -0.08
    Crypto
    -0.07
    CLUDE
    -0.07
    aul
    -0.07
    ÑĪÑĤи
    -0.07
    thy
    -0.07
    aches
    -0.07
    igator
    -0.06
    ainer
    -0.06
    POSITIVE LOGITS
     handbook
    0.09
    æµħæŀIJ
    0.08
    æµħè°Ī
    0.08
     eds
    0.07
     Handbook
    0.07
    è¿Ľä¸ĢæŃ¥æıIJé«ĺ
    0.07
     perspectives
    0.07
    åķĨæĬ¥
    0.07
     aspects
    0.07
    èĭ¥å¹²éĹ®é¢ĺçļĦ
    0.07
    Activations Density 0.349%

    No Known Activations