© 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. 30053
    Prev
    Next
    INDEX
    Explanations

    maximum with following word

    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
    мена
    -0.10
    minster
    -0.10
    seau
    -0.09
    aments
    -0.09
    AWN
    -0.09
    ê¹ĥ
    -0.09
    vang
    -0.08
    dien
    -0.08
    rvine
    -0.08
    bane
    -0.08
    POSITIVE LOGITS
    IMUM
    0.13
    o
    0.10
    s
    0.09
    ات
    0.09
    imum
    0.08
    OrDefault
    0.08
    imal
    0.07
    innacle
    0.07
    illary
    0.07
    oft
    0.07
    Activations Density 0.037%

    No Known Activations