© 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. 1893
    Prev
    Next
    INDEX
    Explanations

    . The

    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
     cram
    -0.07
    ä¸ĸå¤ĸ
    -0.07
    odge
    -0.07
    è¿Ļ个æĺ¯
    -0.06
    è¿Ļ人
    -0.06
    ม
    -0.06
    middel
    -0.06
    lette
    -0.06
    è¿Ļåı¯æĺ¯
    -0.06
    以为æĺ¯
    -0.06
    POSITIVE LOGITS
     nonetheless
    0.08
     Nonetheless
    0.08
    istrator
    0.08
    tron
    0.07
    jur
    0.07
    ownload
    0.07
    istory
    0.07
    ächt
    0.07
    ÃľR
    0.07
     Aware
    0.07
    Activations Density 0.187%

    No Known Activations