© 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. 64358
    Prev
    Next
    INDEX
    Explanations

    romanToInt `č`

    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
    ĥĿ
    -0.08
    engel
    -0.08
    éĵ¶å±±
    -0.07
    çĻ¾å¿Ļ
    -0.07
    кÑĥпа
    -0.07
    APS
    -0.07
    à¹Ģà¸Ĭีย
    -0.07
    马éŀį
    -0.07
    itario
    -0.07
     Assinar
    -0.07
    POSITIVE LOGITS
    ervis
    0.07
    oÅĤ
    0.06
    åd
    0.06
    ä¸ĢæŃ¥æŃ¥
    0.06
    wab
    0.06
    Invoker
    0.06
    orma
    0.06
    çª
    0.06
    uart
    0.06
    unky
    0.05
    Activations Density 0.018%

    No Known Activations