© 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. 9279
    Prev
    Next
    INDEX
    Explanations

    some followed by nouns

    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
    å¤ļä¹ħ
    -0.08
    ä¹ĭä¸Ģ
    -0.08
     ÛĮÚ©ÛĮ
    -0.08
    ä¸Ńä¹ĭ
    -0.08
    æīĢæľī人çļĦ
    -0.08
    à¸Ĺุà¸ģร
    -0.08
    joy
    -0.08
    ä½ķ以
    -0.08
    omad
    -0.07
    ä¸Ńç²®
    -0.07
    POSITIVE LOGITS
    “
    0.10
    å¹´éĩĮ
    0.08
    æĥħåĨµä¸ĭ
    0.08
    诸å¦Ĥ
    0.08
    er
    0.08
    æľīåĪ©äºİ
    0.08
    æŶåĢĻ
    0.08
    ä¸İ该
    0.07
    æĹ¥åŃIJéĩĮ
    0.07
    æīĢè°ĵçļĦ
    0.07
    Activations Density 0.014%

    No Known Activations