© 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. 8404
    Prev
    Next
    INDEX
    Explanations

    life, time, emotion, career

    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
    æłĩåĩĨè¦ģæ±Ĥ
    -0.09
    å¼ı设计
    -0.07
     gross
    -0.07
    缮
    -0.07
    ä¼ĺè¶Ĭ
    -0.06
    æ´ŀéĩĮ
    -0.06
    èĪ¬
    -0.06
    ادÙħ
    -0.06
    gross
    -0.06
    õt
    -0.06
    POSITIVE LOGITS
    å°±åĥıä¸Ģ个
    0.16
    æ¯Ķä½ľ
    0.15
    çĬ¹å¦Ĥ
    0.14
    好æ¯Ķ
    0.14
    就好æ¯Ķ
    0.13
    å°±åĥıæĺ¯
    0.13
    å°±åĥı
    0.13
    åĥıä¸Ģåıª
    0.11
    就好åĥı
    0.11
     بÙħثابة
    0.11
    Activations Density 0.225%

    No Known Activations