© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17763
    Prev
    Next
    INDEX
    Explanations

    yes, read

    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
    ulu
    -0.08
    èµ·çłģ
    -0.08
     perhaps
    -0.07
    å¾Ĺèµ·
    -0.07
    èĮ¬
    -0.07
    —if
    -0.07
    ãģĦãģĭãģĮ
    -0.07
    .Maybe
    -0.07
    (Optional
    -0.06
    æĬĢæľ¯åıijå±ķ
    -0.06
    POSITIVE LOGITS
    ä¸įæĺ¯ä½ł
    0.10
    ä¸įæĺ¯æĪij
    0.10
    ä¸įæĺ¯åľ¨
    0.08
    æ²ĴéĮ¯
    0.08
    ä¸įæĺ¯
    0.08
    oogle
    0.08
    åIJ¬åĪ°äºĨ
    0.07
    并ä¸įæĺ¯
    0.07
    ä¸įæĺ¯ä¸ºäºĨ
    0.07
    åIJ¬åĪ°çļĦ
    0.07
    Activations Density 0.542%

    No Known Activations