© 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. 25451
    Prev
    Next
    INDEX
    Explanations

    preset signal strength

    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
     notwithstanding
    -0.07
    æľĢèijĹåIJįçļĦ
    -0.07
    [:]
    -0.06
     Platz
    -0.06
     pozorn
    -0.06
    æīĢè°ĵ
    -0.06
     embark
    -0.06
    δη
    -0.06
    serter
    -0.06
    inkin
    -0.06
    POSITIVE LOGITS
    æķ´ä½ĵçļĦ
    0.08
     rele
    0.08
     Canter
    0.07
    æĬĬæݧ
    0.07
    าะ
    0.07
    Ws
    0.07
    对åºĶçļĦ
    0.07
    вÑĢ
    0.07
    aurus
    0.07
    urus
    0.07
    Activations Density 0.002%

    No Known Activations