© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 42219
    Prev
    Next
    INDEX
    Explanations

    symbols and numbers

    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
    çĶ¨åĵģ
    -0.07
    åªĴ
    -0.07
    à¸ģà¸ĩ
    -0.07
    .inf
    -0.06
    capital
    -0.06
    ivor
    -0.06
    mdi
    -0.06
    Descriptions
    -0.06
    olib
    -0.06
    å©Ĩ
    -0.06
    POSITIVE LOGITS
    åħ¬æĸĩ
    0.09
    è¡Įæĸĩ
    0.08
    èģĮæĿĥ
    0.08
    èģĮèĥ½
    0.08
    åħ¬åĬ¡
    0.08
    è¡ĮæĶ¿
    0.08
    èģĮåĬ¡
    0.08
    åĦ¿åª³
    0.07
    CIL
    0.07
    æĹłèĻij
    0.07
    Activations Density 0.002%

    No Known Activations