© 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. 37433
    Prev
    Next
    INDEX
    Explanations

    abbreviation/acronym

    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
    ä¹Ŀé¾Ļ
    -0.08
    /cop
    -0.07
    /display
    -0.07
    æĻĮ
    -0.07
    ädt
    -0.07
    coles
    -0.07
    orama
    -0.07
    åĢ¾æĥħ
    -0.07
    etics
    -0.06
    emer
    -0.06
    POSITIVE LOGITS
    ç®Ģ称
    0.11
     abbreviated
    0.10
    abbrev
    0.10
     abbreviation
    0.09
    簡稱
    0.09
    缩åĨĻ
    0.09
    ç®Ģ
    0.08
    inach
    0.07
    aka
    0.07
     acronym
    0.07
    Activations Density 0.522%

    No Known Activations