© 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. 11607
    Prev
    Next
    INDEX
    Explanations

    example / examples

    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
    ç·ıåIJĪ
    -0.08
    综åIJĪåĪĨæŀIJ
    -0.08
    综åIJĪ
    -0.08
    å¾ħ
    -0.07
    è¿ĩé«ĺ
    -0.07
    μÎŃ
    -0.07
    åĨ³å®ļçļĦ
    -0.07
    æĸ©
    -0.07
    åĴĮåIJĦç§į
    -0.07
    .pending
    -0.07
    POSITIVE LOGITS
    ä¾ĭåŃIJ
    0.10
    çļĦä¾ĭåŃIJ
    0.09
    ä¸Ģä¾ĭ
    0.09
     examples
    0.09
     satisfying
    0.09
    /examples
    0.08
     esempi
    0.08
    examples
    0.08
     пÑĢимеÑĢ
    0.08
    example
    0.08
    Activations Density 0.047%

    No Known Activations