© 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. 42527
    Prev
    Next
    INDEX
    Explanations

    computer, media, and technology terms

    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
    æľīå¦Ĥ
    -0.08
    å°ıåŁİ
    -0.07
    _mk
    -0.07
    åĭ¤åĭ¤æģ³æģ³
    -0.07
    ykk
    -0.07
     fert
    -0.07
    _TEXTURE
    -0.07
    æµ·æ¶Ľ
    -0.07
    alan
    -0.07
    elok
    -0.07
    POSITIVE LOGITS
    羣æŃ£æĦıä¹īä¸ĬçļĦ
    0.09
    çļĦå®ļä¹ī
    0.09
     definition
    0.08
    该æľīçļĦ
    0.08
    defined
    0.08
    åIJįåī¯åħ¶å®ŀ
    0.08
    åĽłä¸ºæľī
    0.07
    åºĶåħ·å¤ĩ
    0.07
    å¿ħé¡»åħ·å¤ĩ
    0.07
     officially
    0.07
    Activations Density 0.059%

    No Known Activations