© 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. 38664
    Prev
    Next
    INDEX
    Explanations

    said than

    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
    ศึà¸ģษา
    -0.10
    altar
    -0.09
    er
    -0.09
    说çĻ½äºĨ
    -0.09
    ity
    -0.08
    iť
    -0.08
    ÙħÙĥاÙĨ
    -0.08
     ÐŁÐ¾Ð¿ÑĢо
    -0.08
    rody
    -0.08
    รัà¸IJ
    -0.08
    POSITIVE LOGITS
    è¿ĩçļĦ
    0.08
    eter
    0.08
    ching
    0.08
    çļĦéĤ£æł·
    0.08
    v
    0.08
    å¾ĹæĽ´
    0.07
    iba
    0.07
    äºĨä¸Ģ声
    0.07
    making
    0.07
    eworthy
    0.07
    Activations Density 0.032%

    No Known Activations