© 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. 61517
    Prev
    Next
    INDEX
    Explanations

    anger, frustration, annoyance

    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
    sweise
    -0.08
    æģ©æĢ¨
    -0.07
    owitz
    -0.07
    ç»Ļ人çļĦ
    -0.07
    æĸĩåĵ²
    -0.07
    ain
    -0.07
    ä¹ĭä¸ĢçļĦ
    -0.07
     Grinder
    -0.07
    Watcher
    -0.06
    ugged
    -0.06
    POSITIVE LOGITS
    ä¸įå·²
    0.11
    ä¹ĭæĥħ
    0.11
    ful
    0.10
    fully
    0.09
    çĪĨæ£ļ
    0.09
    ä¹ĭä½Ļ
    0.09
    -filled
    0.09
    ä¸įåĨ³
    0.09
    uous
    0.09
    fulness
    0.09
    Activations Density 0.139%

    No Known Activations