© 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. 862
    Prev
    Next
    INDEX
    Explanations

    chemical suffixes

    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
    åħľ
    -0.08
    åĨ¥
    -0.08
    è¿«
    -0.07
    追
    -0.07
    .SK
    -0.07
    reck
    -0.07
    é»ijè±Ĩ
    -0.07
    åľ¨åİ¿
    -0.07
    åīĶ
    -0.07
    çĪ±ä¸į
    -0.07
    POSITIVE LOGITS
     themselves
    0.08
    ç±»çŃī
    0.08
    enes
    0.08
    ç±»
    0.08
    çī¢åĽº
    0.07
    ç±»åĴĮ
    0.07
    è¿Ļç±»
    0.07
    çļĦä¸Ģç±»
    0.07
    æĹłä¸į
    0.07
    ä¸Ģç±»
    0.07
    Activations Density 0.024%

    No Known Activations