© 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. 10243
    Prev
    Next
    INDEX
    Explanations

    generated code

    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
    åĮ»çĸĹä¿Ŀåģ¥
    -0.08
    enek
    -0.07
    ENE
    -0.07
     MASTER
    -0.06
    åĴĮå°ļ
    -0.06
    zonder
    -0.06
    çļĦæľĢé«ĺ
    -0.06
     giochi
    -0.06
    .Transactional
    -0.06
    -major
    -0.06
    POSITIVE LOGITS
    rary
    0.08
    æ¥Ń
    0.08
    ä¸ļ
    0.07
    å·²æľī
    0.07
    æľīä½ł
    0.07
    apé
    0.07
    ìĹħ
    0.07
    æľīéĥ¨åĪĨ
    0.07
    ä½łä¸Ģ
    0.07
    adá
    0.07
    Activations Density 0.026%

    No Known Activations