© 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. 25264
    Prev
    Next
    INDEX
    Explanations

    timezone, thereof, fruit, time

    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
    .absolute
    -0.06
    QE
    -0.06
    å®ĥä¼ļ
    -0.06
     дÑĥÑħ
    -0.06
    oulos
    -0.06
    ä¿¡æģ¯æŁ¥è¯¢
    -0.06
    ettle
    -0.06
    ILITY
    -0.06
    çļĦäººä¹Ł
    -0.06
    ABI
    -0.06
    POSITIVE LOGITS
    æĪĸ缴æİ¥
    0.09
    éļĻ
    0.07
     módon
    0.07
    ield
    0.07
    =lambda
    0.06
    å°Ķåħĭ
    0.06
    imai
    0.06
    æIJIJ
    0.06
    enen
    0.06
    åIJ¦
    0.06
    Activations Density 0.009%

    No Known Activations