© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 42295
    Prev
    Next
    INDEX
    Explanations

    integer, rational, irrational numbers

    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
    frig
    -0.08
    chern
    -0.08
    elson
    -0.08
    vron
    -0.08
    mosph
    -0.08
    omid
    -0.07
    RequestMethod
    -0.07
    å®
    -0.07
    åĨįä¹Łæ²¡æľī
    -0.07
    áĪĿ
    -0.07
    POSITIVE LOGITS
    æķ´æķ°
    0.09
     integer
    0.09
     integers
    0.08
    integer
    0.08
     comm
    0.08
     decimal
    0.08
    èIJ½èĦļ
    0.08
     denomin
    0.07
    comm
    0.07
    裴
    0.07
    Activations Density 0.009%

    No Known Activations