© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 26946
    Prev
    Next
    INDEX
    Explanations

    U in mathematical expressions

    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
    è¢«ä¾ĽåºĶåķĨ
    -0.07
    cean
    -0.07
    女éĥİ
    -0.07
    æĿ¥è¿ĩ
    -0.07
    å¾·æĭī
    -0.07
    -inc
    -0.07
    STORE
    -0.07
    pch
    -0.07
    è²Į
    -0.07
     cóm
    -0.07
    POSITIVE LOGITS
    æīĢè½½
    0.08
    roe
    0.07
     Kraj
    0.06
    æłĭ
    0.06
    entially
    0.06
    ¾
    0.06
    python
    0.06
    شب
    0.06
     Dos
    0.06
    AndPassword
    0.06
    Activations Density 0.007%

    No Known Activations