© 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. 11157
    Prev
    Next
    INDEX
    Explanations

    sugar phosphates and intermediates

    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
    ķĮ
    -0.07
    éļ¾è¿ĩ
    -0.07
    usat
    -0.07
    à²Ĥತ
    -0.07
    pii
    -0.07
    ķ
    -0.07
    nty
    -0.07
    è¿ijè·Ŀ离
    -0.07
    cto
    -0.07
    åIJĿ
    -0.06
    POSITIVE LOGITS
    eneric
    0.07
    ekyll
    0.07
    -half
    0.07
    åĩıåįĬ
    0.07
    ouble
    0.06
    OrCreate
    0.06
    -widgets
    0.06
    å¤ļç§įæĸ¹å¼ı
    0.06
     regenerated
    0.06
    half
    0.06
    Activations Density 0.004%

    No Known Activations