© 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. 30973
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with exponentiation

    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
    asc
    -0.08
    way
    -0.07
    le
    -0.07
    st
    -0.07
    ä¸įåIJĮæĦı
    -0.06
     me
    -0.06
    te
    -0.06
    Õ«Õ¶
    -0.06
    tas
    -0.06
    iro
    -0.06
    POSITIVE LOGITS
    çİĭä¹ĭ
    0.08
    ForObject
    0.08
    Ñĸл
    0.08
     écl
    0.08
    뢰
    0.07
    opyright
    0.07
    åĩį
    0.07
    ï¾Ĺ
    0.07
    俨
    0.07
    å½»
    0.07
    Activations Density 0.039%

    No Known Activations