© 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. 45382
    Prev
    Next
    INDEX
    Explanations

    Stack Exchange, Troutbeck, Green, year, between

    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
    享
    -0.07
    5
    -0.06
     ‘
    -0.05
    umeric
    -0.05
    estä
    -0.05
    :\
    -0.05
    äºĶèī²
    -0.05
    åĬłæĭ¿å¤§
    -0.05
    ä¸Ģä¸ĭ
    -0.05
    ][$
    -0.05
    POSITIVE LOGITS
    两ä¸į误
    0.08
    ãģ¨ãģĦãģĨè¨Ģèijī
    0.08
    äºĮåŃĹ
    0.08
    åı¯ä»¥çĤ¹åĩ»
    0.08
    ÙĨداÙĨ
    0.07
    èĥİ
    0.07
    Lexer
    0.07
    stup
    0.07
    è¾ŀåİ»
    0.07
     prossimi
    0.07
    Activations Density 0.038%

    No Known Activations