© 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. 29596
    Prev
    Next
    INDEX
    Explanations

    followed by a word ending in "of" or "the"

    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
     ê²ĥìĿ´ê³ł
    -0.16
     ì¢ĭê³ł
    -0.14
     nämlich
    -0.13
     ìĹĨê³ł
    -0.13
     totiž
    -0.13
    ìĹĪê³ł
    -0.13
    )&&(
    -0.13
    íĸĪê³ł
    -0.13
     ìķĦëĭĪê³ł
    -0.13
     ìŀĪìĹĪê³ł
    -0.12
    POSITIVE LOGITS
     thereof
    0.18
     thereafter
    0.17
     accordingly
    0.17
     therein
    0.16
     serta
    0.15
     consequently
    0.14
     afterward
    0.13
     afterwards
    0.12
    ä¸İä¹ĭ
    0.12
     importantly
    0.11
    Activations Density 3.597%

    No Known Activations