© 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. 62952
    Prev
    Next
    INDEX
    Explanations

    scientific notation values

    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
    annya
    -0.08
    :_
    -0.08
    ier
    -0.08
    긴
    -0.07
    atika
    -0.07
    amba
    -0.07
    ستاÙĨ
    -0.07
    å¦Ĥæ½®
    -0.06
    ocrates
    -0.06
    ano
    -0.06
    POSITIVE LOGITS
    »
    0.08
    recision
    0.07
    zeuge
    0.07
    çĪª
    0.07
    vasive
    0.07
    érieure
    0.07
    ovable
    0.07
    çĿĢ
    0.07
    avier
    0.07
    inerary
    0.07
    Activations Density 0.002%

    No Known Activations