© 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. 44969
    Prev
    Next
    INDEX
    Explanations

    technical processing

    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
    '||
    -0.08
    åİħ
    -0.07
    ushi
    -0.07
    åħ¨èº«å¿ĥ
    -0.07
    ussi
    -0.07
    æĦ¿
    -0.07
    еÑĨ
    -0.07
    apr
    -0.07
    æį¢
    -0.07
    hall
    -0.07
    POSITIVE LOGITS
     depending
    0.12
    è¿Ļ两ç§į
    0.12
    两ç§į
    0.11
    depending
    0.10
    ãģĦãģļãĤĮ
    0.10
    åıĸåĨ³äºİ
    0.09
     dependendo
    0.09
     scenarios
    0.09
     whichever
    0.08
    åĪĨåĪ«ä¸İ
    0.08
    Activations Density 0.023%

    No Known Activations