© 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. 31207
    Prev
    Next
    INDEX
    Explanations

    measure theory topics

    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
    anii
    -0.09
    alty
    -0.08
    uate
    -0.07
    åįĹé£İ
    -0.07
    adero
    -0.07
     Tale
    -0.07
    omis
    -0.07
    isola
    -0.07
     ris
    -0.07
    ocked
    -0.07
    POSITIVE LOGITS
    éĢł
    0.09
    絡
    0.08
    éĢłçī©
    0.07
    imagin
    0.07
    ลัà¸ĩ
    0.07
    å¤ĸçķĮ
    0.07
    _ACTIVITY
    0.06
     fascin
    0.06
    ä¸ĥ大
    0.06
     оÑĨенки
    0.06
    Activations Density 0.002%

    No Known Activations