© 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. 16742
    Prev
    Next
    INDEX
    Explanations

    served at a time

    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
    -days
    -0.09
     days
    -0.09
     annual
    -0.08
    æ¯ıå¹´
    -0.08
     Days
    -0.08
     annually
    -0.08
     yearly
    -0.08
     crippling
    -0.08
    æ¯ıå¹´çļĦ
    -0.08
    èººåľ¨åºĬä¸Ĭ
    -0.08
    POSITIVE LOGITS
    示æĦı
    0.10
     discreet
    0.09
    ä¸Ģ两
    0.08
    第ä¸Ģ件äºĭ
    0.08
     momentarily
    0.08
    é»Ļ
    0.08
     etiquette
    0.08
     infrac
    0.08
    åĩłç§ĴéĴŁ
    0.08
     verbal
    0.08
    Activations Density 0.333%

    No Known Activations