© 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. 54991
    Prev
    Next
    INDEX
    Explanations

    causes of

    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
    erset
    -0.08
    omor
    -0.07
     SERV
    -0.07
     каÑģа
    -0.07
     Conjunto
    -0.06
    vore
    -0.06
    å¾ĺå¾Ĭ
    -0.06
    paralleled
    -0.06
    oglob
    -0.06
    彦
    -0.06
    POSITIVE LOGITS
     sources
    0.14
    æĿ¥æºIJ
    0.13
    ources
    0.12
     Sources
    0.12
    åħ¶ä»ĸæĸ¹å¼ı
    0.12
    sources
    0.11
    ä¾ĨæºIJ
    0.11
    SourceType
    0.11
    Sources
    0.11
    /sources
    0.10
    Activations Density 0.235%

    No Known Activations