© 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. 42014
    Prev
    Next
    INDEX
    Explanations

    stellar, galactic, astronomers, galaxies, astronomy

    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
    æŁĶ
    -0.07
    èĵĦ
    -0.07
     Meister
    -0.07
    ugs
    -0.07
    headed
    -0.06
    caffe
    -0.06
     Coca
    -0.06
    æĿ¾å¼Ľ
    -0.06
    uede
    -0.06
    æ¤į
    -0.06
    POSITIVE LOGITS
     stellar
    0.12
    天æĸĩ
    0.12
    stellar
    0.12
    éĵ¶æ²³
    0.12
     Galactic
    0.12
     astronomers
    0.12
     Astroph
    0.11
     galaxies
    0.11
     Astronomy
    0.11
    æģĴæĺŁ
    0.11
    Activations Density 0.119%

    No Known Activations