© 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. 13761
    Prev
    Next
    INDEX
    Explanations

    HTML/code formatting markup

    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
    oord
    -0.08
    è¿Ľä¸ĢæŃ¥å¢ŀ强
    -0.07
    ardon
    -0.07
    verno
    -0.07
    è¿Ľä¸ĢæŃ¥å¼ºåĮĸ
    -0.07
    Ĥ¹
    -0.07
    enor
    -0.07
    çļĦèĥĮåIJİ
    -0.07
    inqui
    -0.07
     further
    -0.06
    POSITIVE LOGITS
    elan
    0.07
    stan
    0.06
    uge
    0.06
    nop
    0.06
    fuse
    0.06
    اط
    0.06
    åĮł
    0.06
    straÃŁe
    0.06
    ahl
    0.06
    în
    0.06
    Activations Density 0.007%

    No Known Activations