© 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. 1538
    Prev
    Next
    INDEX
    Explanations

    objective

    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
    غ
    -0.07
    >true
    -0.07
    æľ¬èī²
    -0.07
    llib
    -0.07
    ÐĽÐ¸
    -0.07
    à¸ĺร
    -0.07
    .rawValue
    -0.06
    umus
    -0.06
    åĩ¡æľ¬ç½ij注æĺİ
    -0.06
    æĪijä¹Łæľī
    -0.06
    POSITIVE LOGITS
    æĢ»ç»ĵå¦Ĥä¸ĭ
    0.07
    æ³ī
    0.07
    ujuan
    0.07
    äºİå¿ĥ
    0.06
    åIJį为
    0.06
    ooky
    0.06
    åľ¨å·¥ä½ľä¸Ń
    0.06
    å°
    0.06
    assel
    0.06
    :"
    0.06
    Activations Density 0.001%

    No Known Activations