© 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. 44331
    Prev
    Next
    INDEX
    Explanations

    result followed by punctuation or method calls

    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
    ованиÑı
    -0.07
    iture
    -0.07
    ponse
    -0.07
    obo
    -0.06
    itudes
    -0.06
    iggins
    -0.06
    ibles
    -0.06
    ÑħождениÑı
    -0.06
    umped
    -0.06
    åĨįèĢħ
    -0.06
    POSITIVE LOGITS
    ing
    0.11
    enho
    0.09
    å©ķ
    0.08
    ingin
    0.08
    ingi
    0.08
    ingss
    0.08
    inga
    0.08
    à¹Īา
    0.08
     Ú¯ÛĮرÛĮ
    0.08
    _:
    0.08
    Activations Density 0.001%

    No Known Activations