© 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. 62066
    Prev
    Next
    INDEX
    Explanations

    angular.module or mathematical symbols

    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
    èİĺ
    -0.08
    Õµ
    -0.07
    hide
    -0.07
    æŃ£æĺ¯åĽłä¸º
    -0.07
    ienes
    -0.07
    éĤij
    -0.07
    ä¸įè¡Į
    -0.07
    è¿IJè¡ĮæŶ
    -0.07
    inary
    -0.06
    æĹłå£°
    -0.06
    POSITIVE LOGITS
    æ´¾çļĦ
    0.07
    æ´¾
    0.07
    å®ļ
    0.07
    èĸ¦
    0.06
    stein
    0.06
    )did
    0.06
    æ´ĭ
    0.06
    ],&
    0.06
    æŁ
    0.06
     ìĶ
    0.06
    Activations Density 0.004%

    No Known Activations