© 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. 43502
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and equations

    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
    uhe
    -0.08
    å·§åIJĪ
    -0.08
    çī¢
    -0.07
    assar
    -0.07
    ä¿¡ä»°
    -0.07
    irk
    -0.07
    erbe
    -0.07
    urato
    -0.07
     Eras
    -0.07
     Macy
    -0.07
    POSITIVE LOGITS
    西æĸ¹åĽ½å®¶
    0.07
    åı¯æĺ¯åľ¨
    0.07
    Western
    0.07
    åı¯æĺ¯æĪij
    0.06
    itr
    0.06
    inst
    0.06
    éĩĮæĸ¯
    0.06
    ç»´æĸ¯
    0.06
    elle
    0.06
    ÐIJÐŀ
    0.06
    Activations Density 0.004%

    No Known Activations