© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 26755
    Prev
    Next
    INDEX
    Explanations

    listing items

    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
    ayani
    -0.06
     regard
    -0.06
    inary
    -0.06
    azer
    -0.06
    ä»ij
    -0.06
     finally
    -0.06
    actical
    -0.06
    ajem
    -0.06
    etrics
    -0.06
    Forg
    -0.06
    POSITIVE LOGITS
    以åıĬåľ¨
    0.08
    ãĢįãĢĮ
    0.08
    äºĨ大éĩıçļĦ
    0.07
    ilu
    0.07
    lds
    0.07
     ìĭ¬ì§Ģìĸ´
    0.07
    ×ŀ×Ļ×Ŀ
    0.07
    Ø«ÙĪر
    0.07
    ucz
    0.07
    пÑĢоÑĩем
    0.07
    Activations Density 0.102%

    No Known Activations