© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 22937
    Prev
    Next
    INDEX
    Explanations

    specific text file extensions

    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
    æľīçĤ¹åĥı
    -0.07
     pate
    -0.07
    igel
    -0.06
    raad
    -0.06
    象
    -0.06
    太å¤ļäºĨ
    -0.06
    就象
    -0.06
    hell
    -0.06
    æħ°èĹī
    -0.06
    odate
    -0.06
    POSITIVE LOGITS
    窩
    0.08
    橱çªĹ
    0.08
    ilden
    0.07
    mayan
    0.07
    .rar
    0.07
    /latest
    0.07
    à¶Ń
    0.07
    <w
    0.07
    .override
    0.07
    è¿ĺæĺ¯éĿŀ常
    0.07
    Activations Density 0.012%

    No Known Activations