© 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. 56356
    Prev
    Next
    INDEX
    Explanations

    fractions and divisions

    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
    äºİä¸ĸ
    -0.07
    oop
    -0.07
    çIJ¥
    -0.06
    ebbe
    -0.06
    åĪ°ä¸ĭ
    -0.06
    çĶ¨æĪ¿
    -0.06
    T
    -0.06
    S
    -0.06
    åĢĴåľ¨
    -0.06
    "-
    -0.06
    POSITIVE LOGITS
    ھا
    0.09
    Äĥm
    0.08
    utes
    0.07
    Convertible
    0.07
    .unknown
    0.07
    ืà¸Ńà¸Ļ
    0.07
    ónimo
    0.07
    лена
    0.07
    fras
    0.07
    ÅĽÄĩ
    0.07
    Activations Density 0.001%

    No Known Activations