© 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. 11168
    Prev
    Next
    INDEX
    Explanations

    Japan and Japanese

    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
    anghai
    -0.08
    rava
    -0.08
    è§ij
    -0.08
    ä¸ŃåĽ½äººæ°ij解æĶ¾åĨĽ
    -0.08
    -0.08
    ouw
    -0.08
    æ·ĭæ¼ĵ
    -0.08
    æīĭæľºç«Ļ
    -0.08
    áu
    -0.07
    andingan
    -0.07
    POSITIVE LOGITS
    佬
    0.08
    unos
    0.07
    æľ¬åľŁ
    0.07
    kar
    0.07
    etus
    0.07
    çļĦä¸ĢäºĽ
    0.07
    çļĦåģļæ³ķ
    0.07
    çon
    0.06
    æŃ¤ä¸¾
    0.06
    itag
    0.06
    Activations Density 0.023%

    No Known Activations