© 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. 15786
    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
    paro
    -0.07
    ëŀ
    -0.07
    awa
    -0.07
    ulam
    -0.07
    mera
    -0.06
    arte
    -0.06
     '*
    -0.06
     näm
    -0.06
    éĹŃ
    -0.06
    ÙĬÙĪ
    -0.06
    POSITIVE LOGITS
    çŃīåĪ°äºĨ
    0.07
    çĮ¬
    0.07
    æĦıæĢĿ
    0.07
    COMPLETE
    0.07
    ²
    0.07
     grandchildren
    0.07
    ieri
    0.07
    resa
    0.07
    rys
    0.07
    ikel
    0.07
    Activations Density 0.010%

    No Known Activations