© 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. 30210
    Prev
    Next
    INDEX
    Explanations

    Transferring or exchanging amounts

    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
     recher
    -0.07
    anj
    -0.07
     stitched
    -0.07
    æīĭåĨĻ
    -0.07
    gj
    -0.07
    ä¸ĩäºĭå¦ĤæĦı
    -0.07
     Dund
    -0.07
    éľ²å¤´
    -0.07
    .geo
    -0.06
    æİĴä½į
    -0.06
    POSITIVE LOGITS
    交æį¢
    0.09
     exchanges
    0.09
     Ðŀбо
    0.09
     overflow
    0.08
     transfer
    0.08
     transfers
    0.08
    .Transfer
    0.08
     exchange
    0.08
    idor
    0.08
     Exchange
    0.08
    Activations Density 0.006%

    No Known Activations