© 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. 12976
    Prev
    Next
    INDEX
    Explanations

    converts or conversions

    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
    éĢīæĭ©ä¸Ģ个
    -0.07
    çģµ
    -0.06
    ioc
    -0.06
    ä¸įåĪĨ
    -0.06
    رش
    -0.06
     Petro
    -0.06
    hd
    -0.06
    illon
    -0.06
     Mark
    -0.06
    çĸ¾çĹħçļĦ
    -0.06
    POSITIVE LOGITS
     пÑĢев
    0.09
    转åĮĸ
    0.09
     تبدÛĮÙĦ
    0.09
    转åĮĸæĪIJ
    0.09
     converts
    0.08
     Converts
    0.08
     convertirse
    0.08
     convertir
    0.08
     converting
    0.08
     conversions
    0.08
    Activations Density 0.063%

    No Known Activations