© 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. 62464
    Prev
    Next
    INDEX
    Explanations

    parentheses followed by numbers or operations

    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
    aced
    -0.07
    vert
    -0.07
    Vert
    -0.07
    èĬĿ麻
    -0.07
    |.
    -0.07
    íŀĪ
    -0.07
    erer
    -0.07
    elter
    -0.06
    ä¸ĭåIJĮ
    -0.06
    alf
    -0.06
    POSITIVE LOGITS
    è¡£èįī
    0.07
    구ëĤĺ
    0.07
    inidad
    0.07
    -Saharan
    0.07
    emento
    0.07
    .keySet
    0.07
     reci
    0.07
    é¦ĸ度
    0.07
    çŁ¥ä¹ĭ
    0.07
    OnInit
    0.07
    Activations Density 0.009%

    No Known Activations