© 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. 34240
    Prev
    Next
    INDEX
    Explanations

    ãģ« after Se

    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
    ×ķ×ķ
    -0.08
    ä¹ĭæĺŁ
    -0.08
    ä¸Ģéĥİ
    -0.08
    ä¸Ńæľī
    -0.08
    WithValue
    -0.07
    ä¸Ńæī¾åĪ°
    -0.07
    ä¸Ńåıijçİ°
    -0.07
    ä¹ĭ
    -0.07
    åľ¨æŁIJ
    -0.07
    ä¹ĭäºİ
    -0.07
    POSITIVE LOGITS
    ãģķãģĪ
    0.08
     ë¶ĢíĦ°
    0.08
    /if
    0.07
    çļĦæĥħæĻ¯
    0.07
    à´¤àµįà´¤
    0.07
    /by
    0.07
    迸
    0.07
    ÙĴÙĨÙİ
    0.07
     ìĿ´ë£¨ìĸ´
    0.07
    ÙĴÙĨ
    0.07
    Activations Density 0.005%

    No Known Activations