© 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. 45735
    Prev
    Next
    INDEX
    Explanations

    Chinese characters and mood, or math $\int f(x)\mathrm{d}x$

    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
    yt
    -0.07
    ansa
    -0.07
    çİ°å°Ĩæľīåħ³äºĭ项
    -0.07
     {}:
    -0.07
    éĤ£è¾¹
    -0.07
    å°ı说éĺħ读
    -0.06
    nios
    -0.06
     ESPECIAL
    -0.06
    åħĦå¼Łä»¬
    -0.06
    vsp
    -0.06
    POSITIVE LOGITS
    æŃ£æĺ¯
    0.11
     appunto
    0.10
     exactly
    0.09
    è¿ĻæŃ£æĺ¯
    0.09
    æŃ£å¥½
    0.09
    ãģ¾ãģķãģ«
    0.08
    å°±æĺ¯ä»ĸ
    0.08
    å°±æĺ¯æĪij们çļĦ
    0.08
    æģ°å¥½
    0.08
    æģ°
    0.08
    Activations Density 0.003%

    No Known Activations