© 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. 18245
    Prev
    Next
    INDEX
    Explanations

    how to / employed / propose

    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
    ä¸į足以
    -0.09
    çĶ¨äºİæ²»çĸĹ
    -0.08
    为äºĨæĽ´å¥½çļĦ
    -0.08
    足以
    -0.08
    æĽ´æľīåĪ©äºİ
    -0.08
    æľīçĽĬäºİ
    -0.08
    ä¸ºè¿Ľä¸ĢæŃ¥
    -0.07
    æķijçģ¾
    -0.07
    çĸ«æĥħéĺ²æݧåĴĮ
    -0.07
    人们对
    -0.07
    POSITIVE LOGITS
     hacerlo
    0.10
     melakukannya
    0.09
    为æѤ
    0.08
    çĶ¨åĪ°çļĦ
    0.08
    使å®ĥ
    0.08
    è¿Ļæł·åģļ
    0.08
    çĶ¨åĪ°
    0.08
     hierfür
    0.08
     farlo
    0.07
    为ä¹ĭ
    0.07
    Activations Density 0.667%

    No Known Activations