© 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. 32525
    Prev
    Next
    INDEX
    Explanations

    variation

    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
    erator
    -0.10
    ihat
    -0.09
    ¤
    -0.08
    einander
    -0.08
    urance
    -0.08
    uston
    -0.07
    abyrin
    -0.07
    ablish
    -0.07
    вно
    -0.07
    ä¹ĭéģ¥
    -0.07
    POSITIVE LOGITS
    IRTUAL
    0.10
    å¼ĢæĿ¥
    0.09
    engeance
    0.09
    ERTICAL
    0.09
    odafone
    0.09
    OLUME
    0.09
    /div
    0.08
    quez
    0.08
    æĢ§çļĦ
    0.08
    शà¥Ģ
    0.08
    Activations Density 0.077%

    No Known Activations