© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 38789
    Prev
    Next
    INDEX
    Explanations

    available, also, only, because, which

    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
    vid
    -0.08
    omie
    -0.07
     Bald
    -0.07
    çī¢
    -0.07
    ä¸ĢåĪĩéĥ½æĺ¯
    -0.07
    aille
    -0.07
    空éĻį
    -0.07
     Prev
    -0.07
    Prev
    -0.07
    Prem
    -0.07
    POSITIVE LOGITS
    ä¹Łæĺ¯ä¸ŃåĽ½
    0.08
    é¡ŀ
    0.08
     szint
    0.07
    ä¹Łæĺ¯æĪij
    0.07
    åĴĮæݨ广
    0.07
    ç±»
    0.07
    ä¹Łæĺ¯æ¯Ķè¾ĥ
    0.07
    ç±»çļĦ
    0.07
     mixed
    0.06
    åı·çļĦ
    0.06
    Activations Density 0.703%

    No Known Activations