© 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. 636
    Prev
    Next
    INDEX
    Explanations

    supporting information files

    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
    ajo
    -0.07
    aw
    -0.07
    atar
    -0.06
    ä¸Ģ群人
    -0.06
    ilio
    -0.06
     Tog
    -0.06
    åĨĴ
    -0.06
    ä¸Ģ个æĸ°çļĦ
    -0.06
    ospel
    -0.06
    .invalidate
    -0.06
    POSITIVE LOGITS
    details
    0.08
     details
    0.08
    çļĦæŃ»
    0.08
    ç»ĨèĬĤ
    0.07
    èĥŀèĥİ
    0.07
    çīĪæľ¬çļĦ
    0.07
     detalles
    0.07
    ä¹ĭ交
    0.07
     IsNot
    0.07
    мони
    0.07
    Activations Density 0.029%

    No Known Activations