© 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. 33067
    Prev
    Next
    INDEX
    Explanations

    numbers following digits

    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
    \
    -0.07
    erenc
    -0.07
    "
    -0.06
    \(
    -0.06
    понен
    -0.06
    -
    -0.06
    \_
    -0.06
    \)
    -0.06
    <
    -0.06
    å¼ıçļĦ
    -0.06
    POSITIVE LOGITS
    зли
    0.07
    #@
    0.07
    bee
    0.07
    让广大
    0.07
    usche
    0.07
    æľĪåīį
    0.07
    Ñĥдо
    0.07
    ddb
    0.07
    untime
    0.06
    ollen
    0.06
    Activations Density 0.608%

    No Known Activations