© 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. 923
    Prev
    Next
    INDEX
    Explanations

    mathematical notation with numbers and symbols

    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
    ermann
    -0.07
    à¸ĺิ
    -0.07
    .inline
    -0.07
    æŦ
    -0.07
    rita
    -0.07
    å¿ĥåĴĮ
    -0.06
    omag
    -0.06
    次åĽŀ
    -0.06
     purposes
    -0.06
    ewood
    -0.06
    POSITIVE LOGITS
    éĺĪåĢ¼
    0.07
     classes
    0.07
    åĪĴ
    0.07
    ä¸īå°º
    0.07
    reshold
    0.07
    åŀĴ
    0.07
    éĺĪ
    0.07
    åĽ´
    0.07
    classes
    0.06
    åĬĥ
    0.06
    Activations Density 0.007%

    No Known Activations