© 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. 56436
    Prev
    Next
    INDEX
    Explanations

    past tense actions and events

    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
     dasar
    -0.09
    ç¤
    -0.08
    ffin
    -0.08
    åĴĮè¡Į为
    -0.07
    retto
    -0.07
    äºĭåıij
    -0.07
    pson
    -0.07
    /moment
    -0.07
    好åIJĹ
    -0.06
    è¾ĵåħ¥çļĦ
    -0.06
    POSITIVE LOGITS
    ä¸İåIJ¦
    0.13
    ness
    0.11
    ç¨ĭ度ä¸Ĭ
    0.10
    /non
    0.08
    /not
    0.08
    äºĨçļĦ
    0.08
    heits
    0.08
    æĪĸ被
    0.07
    éĢļçŁ¥ä¹¦
    0.07
    OwnProperty
    0.07
    Activations Density 0.115%

    No Known Activations