© 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. 32763
    Prev
    Next
    INDEX
    Explanations

    special characters and scanned text

    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
    åŃ¦ä¹łä¹łæĥ¯
    -0.08
    edly
    -0.07
     organ
    -0.07
    cules
    -0.07
    кÑĢÑĥ
    -0.07
    Ĩł
    -0.07
    åĪ¶çļĦ
    -0.07
    éĶ¦æ¶Ľ
    -0.07
    uddy
    -0.07
    ieste
    -0.07
    POSITIVE LOGITS
    زÛĮ
    0.07
    inou
    0.06
    —and
    0.06
     grids
    0.06
    alih
    0.06
     изда
    0.06
    _chunk
    0.06
    篷
    0.06
    æŃ¤åľ°
    0.06
    èµ°è¿ij
    0.06
    Activations Density 0.085%

    No Known Activations