© 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. 8598
    Prev
    Next
    INDEX
    Explanations

    concepts and assessments

    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
    æī«ä¸Ģæī«
    -0.08
    åĴĮæĿ¨
    -0.08
    代çłģå¦Ĥä¸ĭ
    -0.08
    жÑĮ
    -0.08
    è¨Ĺ
    -0.08
    #index
    -0.08
    åĩ¯è¿ª
    -0.08
    zwi
    -0.07
    åı¤å±ĭ
    -0.07
    blr
    -0.07
    POSITIVE LOGITS
    ↵
    0.07
    ï¼Ľ
    0.07
    å®
    0.07
    ä»Ķ
    0.06
    (
    0.06
    æŁIJ
    0.06
    涵
    0.06
    为主线
    0.06
    ï¼Ī
    0.06
    èĺ
    0.06
    Activations Density 0.475%

    No Known Activations