© 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. 51338
    Prev
    Next
    INDEX
    Explanations

    displeased or unhappy about something

    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
    åIJįåī¯
    -0.07
    ÑĢев
    -0.07
    unded
    -0.07
    odable
    -0.07
    ä»ĸå¿ĥéĩĮ
    -0.07
    oreach
    -0.07
    åIJ¸å¼ķ人çļĦ
    -0.07
    bane
    -0.07
    igger
    -0.06
    gence
    -0.06
    POSITIVE LOGITS
    æŀģäºĨ
    0.09
    åıĸå¾ĹçļĦæĪIJ绩
    0.08
    çªģå¦Ĥåħ¶æĿ¥çļĦ
    0.08
    ä»»ä½ķå½¢å¼ıçļĦ
    0.08
     overly
    0.08
    ä¸įå·²
    0.08
    æľīåĬł
    0.07
    å°½ãģı
    0.07
     excessive
    0.07
    éĢıäºĨ
    0.07
    Activations Density 0.424%

    No Known Activations