© 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. 60863
    Prev
    Next
    INDEX
    Explanations

    failure, dysfunction, abnormal, impaired

    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
    åij½
    -0.07
    åħ¨è¿ĩç¨ĭ
    -0.07
    æĹ¢çĦ¶
    -0.07
    aros
    -0.07
    æĺ¯æł¹æį®
    -0.07
    garten
    -0.07
    ä¸ĬçĶ¨
    -0.07
    меÑĢно
    -0.07
    _CALLBACK
    -0.06
    ä¹ŁæľīäºĽ
    -0.06
    POSITIVE LOGITS
    çļĦè¯Ŀ
    0.09
    ãģ«ãģªãĤĭãģ¨
    0.09
    åĪĻä¼ļ
    0.09
    æĪĸ缺
    0.08
    çļĦ話
    0.08
    話
    0.07
    ä»»ä½ķä¸Ģ个
    0.07
    çļĦåIJİæŀľ
    0.07
    åIJİæŀľ
    0.07
     hụt
    0.07
    Activations Density 0.076%

    No Known Activations