© 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. 4664
    Prev
    Next
    INDEX
    Explanations

    in stock or out of stock

    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
    é¾Ļå±±
    -0.07
    วà¸Ļ
    -0.07
    REATE
    -0.07
    ìĸ´ëĵľ
    -0.07
     пÑĢиз
    -0.07
    omos
    -0.07
    ä¹ĭéķ¿
    -0.07
     Meadows
    -0.07
     Pratt
    -0.06
    عÙĦ
    -0.06
    POSITIVE LOGITS
    åĿij
    0.08
    سخ
    0.06
    _hooks
    0.06
    åłª
    0.06
    ieri
    0.06
    åħ¶å®ĥçļĦ
    0.06
    åĨįçľĭçľĭ
    0.06
    ×Ļף
    0.06
    oire
    0.06
    ëģĶ
    0.06
    Activations Density 0.046%

    No Known Activations