© 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. 8718
    Prev
    Next
    INDEX
    Explanations

    code syntax and structure

    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
    æĸ¹éĿ¢çļĦçŁ¥è¯Ĩ
    -0.06
    éĢĤ
    -0.06
     [].
    -0.06
    on
    -0.06
    -0.06
    ry
    -0.06
    讲çļĦ
    -0.06
    èĮĥåĦ¿
    -0.06
    .hasOwnProperty
    -0.06
    åIJįèĥľ
    -0.05
    POSITIVE LOGITS
    lada
    0.08
    olik
    0.08
    æľīæĪIJ
    0.08
    peria
    0.08
     ekse
    0.08
     slags
    0.08
     seksi
    0.08
    appare
    0.08
     **:**
    0.08
    羣æŃ£
    0.07
    Activations Density 0.162%

    No Known Activations