© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 4693
    Prev
    Next
    INDEX
    Explanations

    definition

    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
    Negative Logits
    æīĢåij¨
    -0.08
    ัà¸ĩà¸ģ
    -0.08
    æīĵæĪIJ
    -0.08
    à¸ı
    -0.07
     arran
    -0.07
    å®īæİĴ
    -0.07
    enames
    -0.07
    onen
    -0.07
    Matchers
    -0.07
    à¹Ħหว
    -0.07
    POSITIVE LOGITS
    inition
    0.09
     definitions
    0.08
     definition
    0.08
    èĮĥçķ´
    0.08
    definition
    0.08
     incorporating
    0.07
     Definition
    0.07
     ÑĤеÑĢмина
    0.07
    并举
    0.07
    -definition
    0.07
    Activations Density 0.056%

    No Known Activations