© 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. 57659
    Prev
    Next
    INDEX
    Explanations

    parentheses and braces

    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
    ı
    -0.08
    oglio
    -0.08
    otti
    -0.08
    orno
    -0.07
    olution
    -0.07
    ¹
    -0.07
    gence
    -0.07
    ignon
    -0.07
    itti
    -0.07
    åľ¨
    -0.07
    POSITIVE LOGITS
    aries
    0.13
    raries
    0.12
    اء
    0.10
    Ø©
    0.10
    еÑĢ
    0.10
    ary
    0.09
    रà¥įस
    0.09
    arangan
    0.09
    ersh
    0.09
    swer
    0.09
    Activations Density 0.082%

    No Known Activations