© 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. 46559
    Prev
    Next
    INDEX
    Explanations

    date numbers

    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¸Ģ转
    -0.08
    åıªæĢķ
    -0.08
    ĮĢ
    -0.07
    è¼
    -0.07
    è¾
    -0.07
    ìĭľëĭ¤
    -0.07
    åįģå¤ļ
    -0.07
    YP
    -0.07
    å¼Ģ头
    -0.07
    é¢ľ
    -0.07
    POSITIVE LOGITS
    %M
    0.07
    å·²åĪ°
    0.07
     forall
    0.07
    ''.
    0.07
    illet
    0.06
    æ²¼
    0.06
    ember
    0.06
    
    0.06
    迹
    0.06
    egah
    0.06
    Activations Density 0.112%

    No Known Activations