© 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. 64473
    Prev
    Next
    INDEX
    Explanations

    past tense verbs

    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
    çĮ®çŃĸ
    -0.08
    ubi
    -0.08
    æĿ¥èĩªç½ij绾
    -0.07
    onge
    -0.07
    æĿ¥èĩªäºİ
    -0.07
    etter
    -0.07
    umen
    -0.07
    åIJĪçIJĨåĪ©çĶ¨
    -0.07
    æĦŁæ¿Ģ
    -0.07
    μο
    -0.07
    POSITIVE LOGITS
    å¾Ĺ天
    0.07
    astia
    0.07
    é«ĺéĢŁ
    0.07
    Åijtt
    0.07
    ä¸ĩåį·
    0.07
    á»įc
    0.07
    å¥ı
    0.07
    usy
    0.07
    çĻ»æľº
    0.07
    airport
    0.06
    Activations Density 0.004%

    No Known Activations