© 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. 26119
    Prev
    Next
    INDEX
    Explanations

    comparisons and scientific terms

    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
    é´
    -0.07
    çİĭ家
    -0.07
    çļĦæĦıæĢĿæĺ¯
    -0.07
    çľŁå¥½
    -0.07
    åľ¨èº«
    -0.07
    æ³ķæĺ¯
    -0.07
     Wag
    -0.06
    æľīç¥ŀ
    -0.06
    igno
    -0.06
    çľĭçĶµè§Ĩ
    -0.06
    POSITIVE LOGITS
    çijľ
    0.08
    宸
    0.08
    haar
    0.08
    åŃĺ
    0.08
    PLY
    0.07
    enio
    0.07
    tain
    0.07
    ynt
    0.07
    sov
    0.07
    ['__
    0.07
    Activations Density 0.008%

    No Known Activations