© 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. 3302
    Prev
    Next
    INDEX
    Explanations

    force or column values

    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
    æĥ¹
    -0.08
    Charset
    -0.07
    æĤ¨çļĦè¯Ħ论
    -0.07
    ä¿Ĭ
    -0.07
    δικ
    -0.07
    è¶ħå¤ļ
    -0.07
     desenvol
    -0.07
    ÙĦÙĬÙĩ
    -0.06
    fur
    -0.06
     distinta
    -0.06
    POSITIVE LOGITS
    æīĢæıIJä¾Ľ
    0.08
    æѦéĻµ
    0.07
     data
    0.07
     petr
    0.07
     measurements
    0.07
    å½ķåıĸ
    0.07
     observed
    0.07
    datum
    0.07
    æīĢæıIJä¾ĽçļĦ
    0.06
    åıįæĺł
    0.06
    Activations Density 0.003%

    No Known Activations