© 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. 33619
    Prev
    Next
    INDEX
    Explanations

    with [entity]

    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
    Unnamed
    -0.07
    Äįk
    -0.07
    æīĢè¿°
    -0.07
     itulah
    -0.07
    幸ç¦ıå¿«ä¹IJ
    -0.07
    çݯå¢ĥä¸İ
    -0.07
    Choices
    -0.07
    åĪĨæŀIJä¸İ
    -0.07
    oho
    -0.07
    uentes
    -0.07
    POSITIVE LOGITS
    standing
    0.12
     regard
    0.12
     impunity
    0.11
     regards
    0.11
    stood
    0.11
     respecto
    0.10
    drawing
    0.10
    draw
    0.10
    ered
    0.10
    held
    0.10
    Activations Density 0.539%

    No Known Activations