© 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. 60115
    Prev
    Next
    INDEX
    Explanations

    production

    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
    Not in Any Lists

    No Comments

    Negative Logits
    rna
    -0.09
    imai
    -0.08
    ieber
    -0.08
    hani
    -0.08
    agai
    -0.07
    ighthouse
    -0.07
    æ¯ıä¸Ģ个åѦçĶŁ
    -0.07
    emek
    -0.07
    -await
    -0.07
    大麦
    -0.07
    POSITIVE LOGITS
    æłĩåĩĨ为
    0.07
    ä¸Ģå¤ķ
    0.07
    ç¦ı
    0.07
    好äºĨ
    0.06
    ove
    0.06
    mando
    0.06
    çĻ
    0.06
     STO
    0.06
    çĮĿ
    0.06
     Hogan
    0.06
    Activations Density 0.001%

    No Known Activations