© 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. 57536
    Prev
    Next
    INDEX
    Explanations

    temperature in Kelvin

    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
    ÖĦ
    -0.08
    ừa
    -0.08
    alic
    -0.08
    ção
    -0.07
    ções
    -0.07
    åŁł
    -0.07
    alz
    -0.07
    åĸĿå®Į
    -0.07
    ous
    -0.07
    ëŀĢ
    -0.07
    POSITIVE LOGITS
    lify
    0.08
    itudes
    0.07
    ieten
    0.07
    ยะ
    0.06
    icker
    0.06
    sWith
    0.06
    Convertible
    0.06
     Chancellor
    0.06
    /sites
    0.06
     chút
    0.06
    Activations Density 0.002%

    No Known Activations