© 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. 23958
    Prev
    Next
    INDEX
    Explanations

    supplement / supplementation

    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
    -0.12
    ipples
    -0.11
    chetti
    -0.09
    uality
    -0.09
    liness
    -0.09
    igma
    -0.08
    herits
    -0.08
    cape
    -0.08
    heber
    -0.08
    à§įতà§ģ
    -0.08
    POSITIVE LOGITS
    aneous
    0.08
    /add
    0.08
    æĢ§çļĦ
    0.07
    uce
    0.07
    stract
    0.07
    ton
    0.07
    ary
    0.07
    aire
    0.07
    说æĺİ
    0.07
    inach
    0.07
    Activations Density 0.023%

    No Known Activations