© 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. 13562
    Prev
    Next
    INDEX
    Explanations

    improve quality or properties

    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
    hofer
    -0.07
     coer
    -0.07
    幸ç¦ıçļĦ
    -0.06
    adó
    -0.06
    人ä¹ĭ
    -0.06
    å®īæİĴéĥ¨ç½²
    -0.06
    ç¦Ħ
    -0.06
    å¹´åīį
    -0.06
    Healthy
    -0.06
    沮丧
    -0.06
    POSITIVE LOGITS
    稳å®ļæĢ§åĴĮ
    0.12
    enh
    0.10
     enhanced
    0.10
     functionalities
    0.10
     functionality
    0.10
     improved
    0.10
     Enhanced
    0.10
    Enh
    0.09
     stability
    0.09
    稳å®ļåĴĮ
    0.09
    Activations Density 0.363%

    No Known Activations