© 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. 21776
    Prev
    Next
    INDEX
    Explanations

    unexplained event, classification, headaches, services, syndrome, mood

    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
    eah
    -0.08
     revan
    -0.08
    TriState
    -0.08
    å¾Īå¤ļä¸ľè¥¿
    -0.08
    allen
    -0.08
    Ĵ¤
    -0.07
    agnol
    -0.07
    èĥ½å¤ŁæľīæķĪ
    -0.07
    çĶŁæ´»ä¼ļ
    -0.07
    éĶ¦æłĩ
    -0.07
    POSITIVE LOGITS
    ä¸Ģç«ł
    0.08
     conformidad
    0.08
    æ¦Ĥ念
    0.07
     Annex
    0.07
    ä¸įå¾Ĺ
    0.07
    minster
    0.07
    ìĹŃ
    0.07
    å·¥åķĨè¡ĮæĶ¿
    0.07
    éĢļåĪĻ
    0.06
     Bowman
    0.06
    Activations Density 0.063%

    No Known Activations