© 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. 32383
    Prev
    Next
    INDEX
    Explanations

    i, i, i

    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
    ovia
    -0.07
    游æĪıä»ĭç»į
    -0.07
    æĤ¨çļĦä½įç½®
    -0.07
    wiss
    -0.07
    ameleon
    -0.07
    æľīåħ³äºİ
    -0.07
    éļ¾ä»¥å¿ĺæĢĢ
    -0.07
    æľªæľī
    -0.07
    缮å½ķä¸Ģè§Ī
    -0.07
    ettings
    -0.07
    POSITIVE LOGITS
    irt
    0.07
    eor
    0.07
    \a
    0.07
    inti
    0.07
    ARSE
    0.07
     Rakyat
    0.06
    teo
    0.06
    üst
    0.06
    allo
    0.06
    ocking
    0.06
    Activations Density 0.970%

    No Known Activations