© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48413
    Prev
    Next
    INDEX
    Explanations

    do followed by a verb phrase

    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
    ا
    -0.07
    ëĭ¤ëĭĪ
    -0.07
    s
    -0.07
    ات
    -0.07
    ÙģÙĪ
    -0.07
    à¸Ķัà¸ĩà¸ģลà¹Īาว
    -0.07
    اغ
    -0.07
    ׾×ĺ
    -0.07
    åºŀ大
    -0.07
    alet
    -0.07
    POSITIVE LOGITS
    ä¹ĭ以
    0.08
    ukkan
    0.08
    cket
    0.08
    ìį¨
    0.08
    æĪijä¸Ģ个
    0.07
    æĥ¯äºĨ
    0.07
    imit
    0.07
    umente
    0.07
    ception
    0.07
    å¦Ĥä¸ĭ
    0.07
    Activations Density 0.042%

    No Known Activations