© 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. 50389
    Prev
    Next
    INDEX
    Explanations

    result in consequences

    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
    åĬłè½½ä¸Ń
    -0.07
    mén
    -0.07
    æ¶īéĩijèŀį
    -0.07
    åĪĩå®ŀä¿Ŀéļľ
    -0.07
    ifiers
    -0.07
    ggi
    -0.07
    WithError
    -0.07
    persist
    -0.07
    åĪ«æıIJ
    -0.07
     szop
    -0.07
    POSITIVE LOGITS
    严éĩįåIJİæŀľ
    0.10
     lasting
    0.09
    ä¸įåIJĮç¨ĭ度çļĦ
    0.08
    æĢİæł·çļĦ
    0.08
    à¹ĥหà¹īà¹Ģà¸ģิà¸Ķ
    0.08
    äºĨä¸Ģåľº
    0.08
     loss
    0.07
     temporary
    0.07
     noticeable
    0.07
     greater
    0.07
    Activations Density 0.194%

    No Known Activations