© 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. 29687
    Prev
    Next
    INDEX
    Explanations

    end of mathematical expressions

    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
    åį³
    -0.07
    el
    -0.06
    ensored
    -0.06
    ang
    -0.06
    å½¢
    -0.06
    eller
    -0.06
    åľ°åİ»
    -0.06
    unde
    -0.06
    éĺ¶
    -0.06
    ce
    -0.06
    POSITIVE LOGITS
    retty
    0.09
    iscard
    0.08
    ç«£
    0.08
    /../
    0.08
    enhagen
    0.08
    ardım
    0.07
    /Math
    0.07
    ä¸Ĭæ¦ľ
    0.07
    umentos
    0.07
    poses
    0.07
    Activations Density 0.018%

    No Known Activations