© 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. 30689
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with variables and symbols

    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
    ä¸ĩäºĭå¦ĤæĦı
    -0.07
     Bretagne
    -0.07
     εÏĢ
    -0.07
    iard
    -0.07
    _hpp
    -0.06
     Sar
    -0.06
    äºĶèĬ±
    -0.06
    ä¸Ń游
    -0.06
     widest
    -0.06
    åįĹçľģ
    -0.06
    POSITIVE LOGITS
    ç½ķ
    0.09
    edor
    0.08
    åѤåĦ¿
    0.07
     Pomp
    0.07
    ä¸īæĹł
    0.07
     Clearance
    0.07
    zyst
    0.07
    .clean
    0.07
    åı·çº¿
    0.07
     clearance
    0.07
    Activations Density 0.021%

    No Known Activations