© 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. 2874
    Prev
    Next
    INDEX
    Explanations

    show that

    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
    çļĦä¸Ģåı¥
    -0.07
    emma
    -0.07
    æĬĬä»ĸ
    -0.07
    ä¸Ģå°ģ
    -0.07
    æľ¬æĬ¥
    -0.07
    ér
    -0.07
    ä¸ľè·¯
    -0.07
    å¦Ĥåľ¨
    -0.07
    anel
    -0.07
    åĩłå¤§
    -0.07
    POSITIVE LOGITS
     (!!
    0.07
    ultip
    0.07
    á»ijn
    0.06
    å§ĵ
    0.06
     flexGrow
    0.06
    -ing
    0.06
     ((!
    0.06
    ãģĺãĤĵ
    0.06
    entic
    0.06
    zyn
    0.06
    Activations Density 0.011%

    No Known Activations