© 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. 62136
    Prev
    Next
    INDEX
    Explanations

    while or whereas

    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
    è¿ĶåĽŀé¦ĸ页
    -0.07
     tehát
    -0.07
    HQ
    -0.07
    aka
    -0.06
    ç¹
    -0.06
    ese
    -0.06
     ë§ŀëĬĶ
    -0.06
    æĻĴ
    -0.06
     à¹Ĩ
    -0.06
    adier
    -0.06
    POSITIVE LOGITS
    ä¸İä¹ĭ
    0.08
    åIJİèĢħ
    0.08
    ervis
    0.08
     others
    0.08
    å®ĥä»¬åľ¨
    0.08
    åIJĥåIJĥ
    0.07
    uetype
    0.07
    .ua
    0.07
    ç»ıèIJ¥èĮĥåĽ´åĮħæĭ¬
    0.07
    bett
    0.07
    Activations Density 0.034%

    No Known Activations