© 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. 13023
    Prev
    Next
    INDEX
    Explanations

    only need to

    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
    缸åħ³éĹ®çŃĶ
    -0.07
    çŃīè¿Ľè¡Į
    -0.07
     sonst
    -0.07
    ä¸Ńå¿ĥçŃī
    -0.07
     etc
    -0.07
    ä¸Ģ票
    -0.07
    è´¹çŃī
    -0.07
    年代åĪĿ
    -0.07
    /fw
    -0.07
    راÙħ
    -0.07
    POSITIVE LOGITS
     “âĢ¦
    0.08
     EITHER
    0.08
     quite
    0.08
    èĥ½å¤Łæ»¡è¶³
    0.07
     nemlig
    0.07
    éĥ·
    0.07
    æľĢ为
    0.07
     decidedly
    0.07
    æł¹æľ¬å°±ä¸į
    0.07
    æīĢæĭ¥æľīçļĦ
    0.06
    Activations Density 1.724%

    No Known Activations