© 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. 48173
    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
    marshall
    -0.08
    ä¸į离
    -0.07
    éĶµ
    -0.07
    jik
    -0.07
    念念
    -0.07
    пов
    -0.07
    å¥ĭåıij
    -0.07
    icar
    -0.07
    IELDS
    -0.06
    ধà§įযà§ĩ
    -0.06
    POSITIVE LOGITS
    abe
    0.07
    -Ta
    0.07
    rot
    0.06
    fil
    0.06
    arcer
    0.06
    ê¹Ķ
    0.06
    ROC
    0.06
    ebt
    0.06
    çļĦåıį
    0.06
    Ta
    0.06
    Activations Density 0.063%

    No Known Activations