© 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. 9210
    Prev
    Next
    INDEX
    Explanations

    atmosphere, touchdown, xydar

    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
    аÑı
    -0.06
    IgnoreCase
    -0.06
    ä¸İåīį
    -0.06
    Predicate
    -0.06
    à¥ĩà¤Ł
    -0.05
    -0.05
    ements
    -0.05
    ½
    -0.05
    áž
    -0.05
    eric
    -0.05
    POSITIVE LOGITS
    afort
    0.08
    ê·
    0.08
    uga
    0.08
    <![
    0.08
    OptionsResolver
    0.08
    renom
    0.08
    lobal
    0.08
     determ
    0.08
     Uncategorized
    0.08
    ldb
    0.08
    Activations Density 0.020%

    No Known Activations