© 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. 19574
    Prev
    Next
    INDEX
    Explanations

    financial balance

    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
     ÏĢι
    -0.08
    .getNode
    -0.08
    umn
    -0.08
     nodeName
    -0.08
    /oct
    -0.08
    绣ä¸Ģéĥ¨ç½²
    -0.08
    hood
    -0.07
    Joint
    -0.07
    rix
    -0.07
    ä¸īçŃī
    -0.07
    POSITIVE LOGITS
    æĶ¶æĶ¯
    0.10
    åĩĢé¢Ŀ
    0.10
    åĩĢ
    0.09
     net
    0.09
    å·®é¢Ŀ
    0.09
    åĩĢæµģåĩº
    0.08
    åıĺåĬ¨
    0.08
    å¾ĢæĿ¥
    0.08
     Net
    0.08
    åĪĨ项
    0.08
    Activations Density 0.005%

    No Known Activations