© 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. 49433
    Prev
    Next
    INDEX
    Explanations

    country or publication names

    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
    lix
    -0.06
    人家
    -0.06
     ...
    -0.06
    äºĶåįĥ
    -0.06
    åIJŁ
    -0.06
    å¯Į强
    -0.05
    ãĥ¼ãĤº
    -0.05
     descu
    -0.05
     proport
    -0.05
    <quote
    -0.05
    POSITIVE LOGITS
    anou
    0.08
    è´¨çļĦ
    0.07
    номо
    0.07
    å¾ħç»Ń
    0.07
    luš
    0.07
    amakan
    0.07
    æľĢè¿ijæĽ´æĸ°
    0.07
    ĩ´
    0.07
    )}.
    0.07
    ại
    0.07
    Activations Density 0.357%

    No Known Activations