© 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. 21164
    Prev
    Next
    INDEX
    Explanations

    giant, enormous, massive

    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
    轻微çļĦ
    -0.09
    çķ¥å¾®
    -0.08
    æ¯Ķè¾ĥç®Ģåįķ
    -0.08
    æľīäºĭ
    -0.08
    å°ıå·§
    -0.08
    è¿Ļ个å°ı
    -0.08
    çĤ¹æ»´
    -0.08
     Tiny
    -0.07
    çķ¥æĺ¾
    -0.07
    åĩłåĪĨ
    -0.07
    POSITIVE LOGITS
    å·¨åŀĭ
    0.19
     massive
    0.18
     colossal
    0.18
     gigantic
    0.18
     enormous
    0.17
    çļĦ巨大
    0.17
     huge
    0.17
    巨大
    0.17
    è¶ħ大
    0.16
    巨大çļĦ
    0.16
    Activations Density 1.235%

    No Known Activations