© 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. 47008
    Prev
    Next
    INDEX
    Explanations

    otherwise or remainder

    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
    åĪļä¸Ģ
    -0.07
    ØŃØ©
    -0.07
     now
    -0.06
    ãģłãģijãģ§ãģ¯ãģªãģı
    -0.06
     ëĭ¤ìĿĮ
    -0.06
     next
    -0.06
    æĽ¾è¡¨ç¤º
    -0.06
    emer
    -0.06
    lya
    -0.06
    ¬ģ
    -0.06
    POSITIVE LOGITS
    åħ¶ä½Ļ
    0.12
    åIJĦè¡Į
    0.11
     Otherwise
    0.09
    _else
    0.09
    åħ¶ä»ĸçļĦ
    0.09
    otherwise
    0.09
    Otherwise
    0.08
    ä¸įçĦ¶
    0.08
     оÑģÑĤалÑĮнÑĭÑħ
    0.08
    åħ¶é¤ĺ
    0.08
    Activations Density 0.101%

    No Known Activations