© 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. 58271
    Prev
    Next
    INDEX
    Explanations

    FFmpeg or video file parts

    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
    à¯įà®ķ
    -0.13
    à¯įய
    -0.10
    deaux
    -0.09
    å·¥åķĨæĪ·
    -0.09
    IÃĵN
    -0.09
    ANNOT
    -0.09
    Ö¼
    -0.09
    ÙĭÙijا
    -0.09
    à§įস
    -0.09
    anski
    -0.09
    POSITIVE LOGITS
    ington
    0.10
    ened
    0.09
    ormsg
    0.08
    ihilation
    0.08
    åĽŀæĹıèĩªæ²»åĮº
    0.08
     ëĤĺìĦľ
    0.08
    ointments
    0.08
    halb
    0.07
    sworth
    0.07
    èĢĮå¦Ĥä»Ĭ
    0.07
    Activations Density 2.846%

    No Known Activations