© 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. 20145
    Prev
    Next
    INDEX
    Explanations

    parenthetical punctuation

    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
     cela
    -0.07
    ynchronously
    -0.07
    è¿Ļåı¯
    -0.06
    åĽł
    -0.06
     بعدÙĩا
    -0.06
    ®
    -0.06
    åħĭç½Ĺ
    -0.06
    w
    -0.06
    ä¸ŃåİŁ
    -0.06
     except
    -0.05
    POSITIVE LOGITS
    Lastly
    0.09
    GRE
    0.08
    åħ¼æĢ»ç»ıçIJĨ
    0.08
     *****
    0.08
    èques
    0.08
    EqualTo
    0.08
    سة
    0.08
    arÄĥ
    0.08
    agama
    0.08
    马åĬĽ
    0.08
    Activations Density 0.001%

    No Known Activations