© 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. 44285
    Prev
    Next
    INDEX
    Explanations

    version and related terminology

    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
    keiten
    -0.06
     '
    -0.06
    اÙģ
    -0.06
    iphery
    -0.06
     ‘
    -0.06
    /manage
    -0.06
    оÑĢ
    -0.06
    _traits
    -0.06
    ãĤ¶
    -0.06
    两ä¸į误
    -0.06
    POSITIVE LOGITS
    ãģ¨åij¼ãģ°ãĤĮãĤĭ
    0.12
    -like
    0.09
    ctl
    0.09
    antro
    0.08
    äºĮ段
    0.08
    buster
    0.08
    IRC
    0.08
    ãģıãģłãģķãģĦãģ¾ãģĽ
    0.08
    lips
    0.08
    ainless
    0.07
    Activations Density 0.422%

    No Known Activations