© 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. 38619
    Prev
    Next
    INDEX
    Explanations

    presenting information

    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
     \(
    -0.07
    åĶ¯ä¸Ģ
    -0.07
    è°ĥæķ´åIJİ
    -0.06
     \
    -0.06
    京
    -0.06
    ____
    -0.06
     sole
    -0.06
     containing
    -0.06
     $
    -0.06
    ä¸Ĭè¿°
    -0.06
    POSITIVE LOGITS
    onti
    0.09
    systems
    0.09
    çĦ¶åIJİæĺ¯
    0.09
    ä¸Ģç½ij
    0.08
    èĢĮéĤ£äºĽ
    0.08
     Thatcher
    0.08
    å¾Īå¤ļä¸ľè¥¿
    0.08
    æ¯ıä¸Ģ个åѦçĶŁ
    0.08
    &,
    0.08
    zano
    0.08
    Activations Density 0.001%

    No Known Activations