© 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. 755
    Prev
    Next
    INDEX
    Explanations

    rates of success/failure

    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
    罪
    -0.06
    apot
    -0.06
     Schaden
    -0.06
    оÑı
    -0.06
    utto
    -0.06
    sieme
    -0.06
    西æĸ¯
    -0.06
    y
    -0.06
    ç¼ĵæħ¢
    -0.05
    æĵįåľºä¸Ĭ
    -0.05
    POSITIVE LOGITS
    çİĩè¾¾
    0.19
    çİĩ
    0.19
    çİĩ为
    0.18
    çİĩè¾¾åĪ°
    0.18
    çİĩåĴĮ
    0.18
    çİĩé«ĺ
    0.17
    çİĩåľ¨
    0.16
    çİĩãģ¯
    0.15
    æĪIJåĬŁçİĩ
    0.15
    çİĩçļĦ
    0.15
    Activations Density 0.641%

    No Known Activations