© 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. 15959
    Prev
    Next
    INDEX
    Explanations

    production related terms

    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
     nhau
    -0.11
    ¾¸
    -0.08
    opard
    -0.08
    à¹īาà¸Ļ
    -0.08
    appa
    -0.08
    -than
    -0.08
    oogle
    -0.08
    gence
    -0.08
    plorer
    -0.08
    ÄĽÅĻ
    -0.08
    POSITIVE LOGITS
    stätten
    0.09
    manship
    0.08
    åĴĮéĶĢåĶ®
    0.08
    ively
    0.08
    (chan
    0.08
    ä¸İéĶĢåĶ®
    0.07
    /output
    0.07
    erta
    0.07
    zier
    0.07
    åıĬéĶĢåĶ®
    0.07
    Activations Density 0.048%

    No Known Activations