© 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. 37762
    Prev
    Next
    INDEX
    Explanations

    column headers and keys

    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
    ï¸ı
    -0.08
    äºĪ
    -0.08
    ï¸İ
    -0.07
    ÑĢин
    -0.07
    trit
    -0.07
     ëĭ¤ìĿĮìĿĢ
    -0.07
    æī©å±ķèµĦæĸĻ
    -0.07
    elling
    -0.07
    åŃIJéĩĮ
    -0.07
    åħ¶æŀĹ
    -0.07
    POSITIVE LOGITS
    åĢĴä¹Ł
    0.07
    åĴĮå¤ĦçIJĨ
    0.07
    å¿«æĬ¥
    0.07
    bot
    0.07
    _FAST
    0.07
    Ñħа
    0.07
    niec
    0.06
    competitive
    0.06
    ugg
    0.06
    astr
    0.06
    Activations Density 0.015%

    No Known Activations