© 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. 18137
    Prev
    Next
    INDEX
    Explanations

    adjective describing state or quality

    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
    人被
    -0.10
    çļĦä¸ĢåĪĩéĥ½
    -0.09
    ÑĬÑĤ
    -0.09
    ä¸įè§ģäºĨ
    -0.08
    ниÑıÑĤ
    -0.08
    urt
    -0.08
    åĴĮè°IJåıijå±ķ
    -0.08
    bey
    -0.08
    æĭĽçĶŁå·¥ä½ľ
    -0.07
     Maggi
    -0.07
    POSITIVE LOGITS
    igem
    0.07
    rone
    0.07
    诸å¦Ĥ
    0.07
     behalf
    0.07
    æĹłå¼Ĥ
    0.07
    ä¸Ķåħ·æľī
    0.06
    à¹Ĩ
    0.06
    igi
    0.06
    ä¸Ķ
    0.06
    ä¸Ķä¸į
    0.06
    Activations Density 0.262%

    No Known Activations