© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 64233
    Prev
    Next
    INDEX
    Explanations

    Chinese and Japanese words

    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
    elog
    -0.09
    ÙħÙĨÙĬ
    -0.08
    IZES
    -0.08
    éŃĶæĹı
    -0.08
    RelativeTo
    -0.08
    POCH
    -0.08
    ztat
    -0.08
    éĿŀçī©è´¨
    -0.08
    å¦ĤæѤä¸ĢæĿ¥
    -0.07
    çłĶ究åıijçİ°
    -0.07
    POSITIVE LOGITS
    æľ¬é¢ĺ
    0.08
     nowadays
    0.08
    ä»ĬåĽŀãģ®
    0.08
    è¿ijæľŁ
    0.08
    æľĢè¿ij
    0.07
    å°¤åħ¶
    0.07
    æīĢ以对äºİ
    0.07
    对äºİä¸Ģ个
    0.07
    对äºİæĪij们
    0.07
    åĥıä½ł
    0.07
    Activations Density 0.216%

    No Known Activations