© 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. 21027
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with exponents

    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
     Redistribution
    -0.07
    roscope
    -0.07
    ricos
    -0.06
    estad
    -0.06
    plor
    -0.06
    oves
    -0.06
    âĨ³
    -0.06
    ãĤģãģIJ
    -0.06
    ami
    -0.06
    bjerg
    -0.06
    POSITIVE LOGITS
    abra
    0.07
    psilon
    0.07
    ivable
    0.07
    ä¹ĭä¹ħ
    0.07
    פ×ķת
    0.07
     mol
    0.06
    tement
    0.06
    aglia
    0.06
    aday
    0.06
    declar
    0.06
    Activations Density 0.103%

    No Known Activations