© 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. 39222
    Prev
    Next
    INDEX
    Explanations

    redundant files

    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
    retty
    -0.07
    rouw
    -0.07
    èģĮä¸ļæĬĢæľ¯åѦéĻ¢
    -0.07
    Iterable
    -0.07
    ButtonDown
    -0.07
     ìłĦë°ĺ
    -0.07
    è¿Ļä¹Łæĺ¯
    -0.07
    impin
    -0.07
    hower
    -0.07
    å¹¿æ³Ľå®£ä¼ł
    -0.07
    POSITIVE LOGITS
    çļĦåŃĺåľ¨
    0.11
    å¤ļä½Ļ
    0.11
     optional
    0.10
    å¤ļä½ĻçļĦ
    0.10
    added
    0.10
     removable
    0.10
    æĹłçĶ¨
    0.10
     presence
    0.10
     added
    0.10
    /remove
    0.09
    Activations Density 0.237%

    No Known Activations