© 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. 60724
    Prev
    Next
    INDEX
    Explanations

    circumference and related words

    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
    رج
    -0.09
    ê³±
    -0.09
    bits
    -0.09
    stvÃŃ
    -0.08
     ủi
    -0.08
    вига
    -0.08
    asmine
    -0.08
    oriously
    -0.08
    OURCE
    -0.08
    cing
    -0.08
    POSITIVE LOGITS
    ächt
    0.08
    оз
    0.07
    ances
    0.07
    avanaugh
    0.07
    ëŁ¼
    0.07
    ichael
    0.06
    ely
    0.06
    èĭ«
    0.06
    çľĭ好çļĦ
    0.06
    à¸ĭà¸Ńย
    0.06
    Activations Density 0.021%

    No Known Activations