© 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. 1428
    Prev
    Next
    INDEX
    Explanations

    questions about "is", "are", "how"

    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
    对ä¸Ĭè¿°
    -0.11
    èĥ½åģļ
    -0.08
    ļľ
    -0.08
    æľīæĿ¡ä»¶
    -0.08
    opsy
    -0.07
    deaux
    -0.07
    åݻ买
    -0.07
     obviously
    -0.07
    æĪij们家
    -0.07
    çĶ¨è¡ĮåĬ¨
    -0.07
    POSITIVE LOGITS
    bard
    0.07
     Mitra
    0.07
    FM
    0.07
    å¢Ł
    0.07
    
    0.07
    è¼Ķ
    0.07
    adays
    0.07
    é«ĺçŃī
    0.06
     bot
    0.06
    .setEditable
    0.06
    Activations Density 0.035%

    No Known Activations