© 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. 38770
    Prev
    Next
    INDEX
    Explanations

    depending on

    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
    æĸ¹å¼ı为
    -0.08
    è´¹çĶ¨çĶ±
    -0.08
    ä¹ĭä¸ĢçļĦ
    -0.08
    ||(
    -0.08
    elte
    -0.07
    ®
    -0.07
    æĺĬ天
    -0.07
    pite
    -0.07
    åĨħ容åĮħæĭ¬
    -0.07
    statuses
    -0.07
    POSITIVE LOGITS
    èĢĮå®ļ
    0.12
    æĺ¯åIJ¦ä¸º
    0.10
    æĺ¯åIJ¦åľ¨
    0.10
     whether
    0.10
    whether
    0.10
    æĺ¯åIJ¦
    0.10
    Whether
    0.09
     Whether
    0.09
    ëĬIJëĥIJ
    0.09
    æĺ¯åIJ¦æľī
    0.08
    Activations Density 0.145%

    No Known Activations