© 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. 27630
    Prev
    Next
    INDEX
    Explanations

    measure word followed by noun

    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
    翼翼
    -0.12
    ä¹ĭåĪĥ
    -0.10
    çĦ¶å¤§
    -0.10
     Ñıка
    -0.09
    ä¹ĭéŨ
    -0.09
    çĦ¶æĺ¯
    -0.09
    emberg
    -0.09
    好æĸĩ
    -0.09
    ä¹ĭåīij
    -0.09
    zion
    -0.08
    POSITIVE LOGITS
    æĪĸå¤ļ个
    0.10
    å¤ļæľĪ
    0.10
    “
    0.09
    å¤ļæľĪçļĦ
    0.09
    ÑģÑı
    0.08
    å¤ļå°ıæŶ
    0.08
    åľ°æĸ¹çļĦ
    0.07
    leges
    0.07
    å±ĤéĿ¢çļĦ
    0.07
    -shot
    0.07
    Activations Density 0.002%

    No Known Activations