© 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. 26022
    Prev
    Next
    INDEX
    Explanations

    citation markers

    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
    azer
    -0.07
    ä¹ħèĢĮ
    -0.07
    -fr
    -0.07
    è¦Ĩ
    -0.07
    enthe
    -0.07
    ä¸Ģæĸ¹çļĦ
    -0.06
    lav
    -0.06
    malink
    -0.06
    eam
    -0.06
    /form
    -0.06
    POSITIVE LOGITS
    адÑĮ
    0.08
     вÑĭл
    0.08
    anlage
    0.08
    witz
    0.07
    abela
    0.07
    ÑĪÑĤ
    0.07
     <!--[
    0.07
    ì½
    0.07
    /providers
    0.07
    åıŃ
    0.07
    Activations Density 0.031%

    No Known Activations