© 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. 58693
    Prev
    Next
    INDEX
    Explanations

    convex analysis and optimization

    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
    INGS
    -0.08
    ings
    -0.08
    ä¸Ģå®ļçļĦ
    -0.08
    urement
    -0.07
    vern
    -0.07
    ungsweise
    -0.06
    annis
    -0.06
    ustry
    -0.06
    ged
    -0.06
    вÑı
    -0.06
    POSITIVE LOGITS
    ä½Ĩä¸įéĻIJäºİ
    0.10
    ly
    0.09
    IBLE
    0.09
    ÙĬØ©
    0.09
    ائص
    0.09
    ibility
    0.09
    uous
    0.08
    antor
    0.08
    åĬŀåħ¬åİħ
    0.08
    idio
    0.08
    Activations Density 0.009%

    No Known Activations