© 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. 22117
    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
    ellini
    -0.07
    ellino
    -0.06
    èĢģåŃIJ
    -0.06
    ellate
    -0.06
     ìĭłê³ł
    -0.06
    ä¼Ĺå¤ļçļĦ
    -0.06
    iaux
    -0.06
    elsey
    -0.06
    ette
    -0.06
    å®Ŀåīij
    -0.06
    POSITIVE LOGITS
    æ··åIJĪ
    0.08
    geg
    0.07
    å¥Īä½ķ
    0.07
    èļĢ
    0.07
    åIJ«éĩı
    0.07
    åIJĪ
    0.07
    Matcher
    0.07
    -txt
    0.07
    åŃķ
    0.07
    chie
    0.07
    Activations Density 0.004%

    No Known Activations