© 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. 40593
    Prev
    Next
    INDEX
    Explanations

    closing parenthesis followed by math or definitions

    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
    ulu
    -0.08
    isty
    -0.08
    anke
    -0.08
    Invoker
    -0.07
    üle
    -0.07
    bred
    -0.07
    egy
    -0.07
    quam
    -0.07
    иÑģÑĤÑĢи
    -0.07
    ulin
    -0.07
    POSITIVE LOGITS
    两个
    0.07
    ³³³
    0.07
     móc
    0.07
    a
    0.06
    åIJĮ
    0.06
    ³³³³
    0.06
    تÙĩ
    0.06
    tn
    0.06
     McCl
    0.06
    çİĩçļĦ
    0.06
    Activations Density 0.009%

    No Known Activations