© 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. 61270
    Prev
    Next
    INDEX
    Explanations

    multiplying or dividing fractions

    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
    缸åħ³æݨèįIJ
    -0.09
    stown
    -0.08
    inki
    -0.07
    å¸Ĩ
    -0.07
    ArrayOf
    -0.07
    _embedding
    -0.07
    ecker
    -0.07
    lacht
    -0.07
    çľł
    -0.07
    strup
    -0.07
    POSITIVE LOGITS
    гаÑĢ
    0.06
    ved
    0.06
    ä¸įèĩªè§ī
    0.06
    idere
    0.06
    tring
    0.06
    ãĤĴå¤ī
    0.06
    .broadcast
    0.06
     physic
    0.06
    太éĥİ
    0.06
     unwitting
    0.06
    Activations Density 0.002%

    No Known Activations