© 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. 14913
    Prev
    Next
    INDEX
    Explanations

    ISO-FIX, TDD, EXIM, OCT

    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¿¡æģ¯çŃī
    -0.07
    æīĢåIJ«
    -0.07
    æĻĵ举
    -0.06
    orni
    -0.06
    绿油
    -0.06
    itur
    -0.06
    ulti
    -0.06
    uluh
    -0.06
    kov
    -0.06
    ensk
    -0.06
    POSITIVE LOGITS
    ëŀĢ
    0.07
    ØŃÙĩ
    0.07
    unner
    0.07
    blast
    0.07
    ä¸ī个åŃĹ
    0.06
     bÃłng
    0.06
    åı¯æľĽ
    0.06
    翼翼
    0.06
    ysize
    0.06
    åĽŀåĽ½
    0.06
    Activations Density 0.871%

    No Known Activations