© 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. 44219
    Prev
    Next
    INDEX
    Explanations

    numbers and counts

    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
    çļĦ
    -0.11
    sWith
    -0.11
    ãģĹãĤĩ
    -0.09
    缸è¾ħ缸æĪIJ
    -0.09
    боÑĢ
    -0.09
    à¯į
    -0.09
    ores
    -0.09
    د
    -0.09
    ãģ®
    -0.08
    à¸Ħà¹Į
    -0.08
    POSITIVE LOGITS
    ä¸Ģæķ°
    0.12
    ä¸įèĥľæķ°
    0.12
    ameleon
    0.08
    ؤ
    0.08
    issance
    0.08
    Ìģ
    0.08
    ptions
    0.08
    elsea
    0.08
    ption
    0.08
    lessly
    0.08
    Activations Density 0.002%

    No Known Activations