© 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. 57888
    Prev
    Next
    INDEX
    Explanations

    HTML and header files

    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
    cci
    -0.07
    HOR
    -0.07
    ãģ£ãģ±ãĤĬ
    -0.07
    Ïģε
    -0.07
     reopening
    -0.07
     Parc
    -0.07
    .tc
    -0.06
    ÏĥÏĩ
    -0.06
     желе
    -0.06
    秧
    -0.06
    POSITIVE LOGITS
    vors
    0.07
    .Syntax
    0.07
    丽ä¸Ŀ
    0.07
    çoit
    0.07
    æѦæĺĮ
    0.06
    åĴĮè§ĦèĮĥ
    0.06
     fa
    0.06
    AlmostEqual
    0.06
    ìĨ
    0.06
    eref
    0.06
    Activations Density 0.284%

    No Known Activations