© 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. 27677
    Prev
    Next
    INDEX
    Explanations

    numbers and degree Celsius

    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
    hawk
    -0.08
    íĮħ
    -0.07
    ttp
    -0.07
    ä¸įæĶ¶
    -0.07
    arella
    -0.07
    olated
    -0.07
    edian
    -0.06
    awk
    -0.06
    è«ĩ
    -0.06
    asih
    -0.06
    POSITIVE LOGITS
    ä¸Ģæīĭ
    0.08
    ev
    0.07
    å¾ĴåĪij
    0.07
    æķĮ
    0.07
    ä¿ĿéļľæĢ§
    0.07
    idency
    0.07
    ebro
    0.07
    uve
    0.07
    å¡«åŁĭ
    0.07
    æĸ¹æ¡ĪåĴĮ
    0.07
    Activations Density 0.064%

    No Known Activations