© 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. 47890
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas or code snippets

    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
    æİīäºĨ
    -0.08
    æİī
    -0.08
    æİīçļĦ
    -0.08
    ä¹ĭåıĪ
    -0.07
    æĬĵå®ŀ
    -0.07
    大è¯Ŀ
    -0.07
    ä¸ĭæĿ¥
    -0.07
    çİĭä¹ĭ
    -0.06
    OTAL
    -0.06
    mier
    -0.06
    POSITIVE LOGITS
    éth
    0.08
    adders
    0.07
    irth
    0.07
    uelas
    0.07
    гүй
    0.07
    бÑĢÑı
    0.07
    ÑĢÑİ
    0.07
    illers
    0.07
    ontos
    0.07
    ials
    0.07
    Activations Density 0.015%

    No Known Activations