© 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. 59098
    Prev
    Next
    INDEX
    Explanations

    technical programming terms

    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
    IDEO
    -0.07
    oth
    -0.07
    ansch
    -0.07
    ä¸į移
    -0.07
    ió
    -0.07
    鸦
    -0.07
    YPE
    -0.07
    passen
    -0.07
    ä¸Ģ缮
    -0.07
    nier
    -0.07
    POSITIVE LOGITS
    代ãģ®
    0.07
    à¹Ģหล
    0.06
    icie
    0.06
    chutz
    0.06
    azos
    0.06
     consts
    0.06
     occured
    0.06
    à´ķ
    0.06
    æľĿ天
    0.06
    åĪĩå°Ķ
    0.06
    Activations Density 0.002%

    No Known Activations