© 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. 13580
    Prev
    Next
    INDEX
    Explanations

    prime factors or common denominators

    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
    ÉĻrÉĻ
    -0.08
     Grosso
    -0.08
    Ĵáŀ
    -0.08
    eced
    -0.07
    å·¥ç¨ĭå¸ĪæĭĽèģĺ
    -0.07
    arrant
    -0.07
    sak
    -0.07
    ndice
    -0.07
    ש×ķ×ij
    -0.07
     Febru
    -0.07
    POSITIVE LOGITS
    ono
    0.07
    оÑĤа
    0.06
    aus
    0.06
    ulon
    0.06
    é¢ĸ
    0.06
    å¼łå»º
    0.06
    avy
    0.06
     dam
    0.06
    dal
    0.06
    代
    0.06
    Activations Density 0.009%

    No Known Activations