© 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. 33600
    Prev
    Next
    INDEX
    Explanations

    algebraic 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
    emet
    -0.07
    åħ¨éķ¿
    -0.07
    èĩªæݧ
    -0.07
    oh
    -0.07
    纵
    -0.07
    à¦ķা
    -0.06
    å®ı
    -0.06
     lineno
    -0.06
    纵åIJij
    -0.06
    fru
    -0.06
    POSITIVE LOGITS
    ίÏīν
    0.08
    ä¸ĭä¸Ģ个
    0.08
    ummings
    0.07
    coni
    0.07
    篱
    0.07
    ä¸ĭä¸Ģ
    0.07
     intermediate
    0.07
    ZIA
    0.07
     Pej
    0.07
    ziem
    0.07
    Activations Density 0.033%

    No Known Activations