© 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. 56628
    Prev
    Next
    INDEX
    Explanations

    deleteItems, Luoluopo, skiing, Truck, uni-versal

    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
    ä¸Ĭä¸Ģç¯ĩ
    -0.07
    æĸij马
    -0.06
    å¦ĤåĽł
    -0.06
    eran
    -0.06
     Brook
    -0.06
     Ben
    -0.06
    loud
    -0.06
     гÑĢом
    -0.06
    MOTE
    -0.06
     Garrison
    -0.06
    POSITIVE LOGITS
    ukkan
    0.08
    IVERS
    0.08
    iversal
    0.08
    ncy
    0.08
    å·¥ç¨ĭéĻ¢
    0.07
     destru
    0.07
    ampion
    0.07
    åĪĨåĪ«ä¸İ
    0.07
    ç¿°
    0.07
    ubl
    0.07
    Activations Density 0.034%

    No Known Activations