© 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. 32394
    Prev
    Next
    INDEX
    Explanations

    doubling, doubled, or tripled

    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
    umon
    -0.07
    èĦ±ä¸ĭ
    -0.07
    alon
    -0.07
    zkod
    -0.07
    éma
    -0.07
    á»ı
    -0.07
    unan
    -0.07
    empa
    -0.06
    çĽ¸ä¼¼æĸĩçĮ®
    -0.06
    unik
    -0.06
    POSITIVE LOGITS
    ä¸ĢåĢį
    0.11
     ÙĪÙĨصÙģ
    0.10
    两åĢį
    0.10
    åĢįçļĦ
    0.10
     lipat
    0.10
    ä¸īåĢį
    0.10
     doubling
    0.10
     تÙĤرÙĬب
    0.09
    ç¿»åĢį
    0.09
     Twice
    0.09
    Activations Density 0.035%

    No Known Activations