© 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. 41936
    Prev
    Next
    INDEX
    Explanations

    transaction, transfer, migrations, trades, adjustments

    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
    ader
    -0.08
    ewidth
    -0.07
    gaste
    -0.07
    /******/
    -0.07
    æij©
    -0.07
     <|
    -0.07
    访éĹ®æŶéĹ´
    -0.07
     ePub
    -0.07
    éĢĥçĶŁ
    -0.07
    è²»
    -0.07
    POSITIVE LOGITS
    åĪĨå½ķ
    0.12
    转移
    0.09
    åĬ¨çĶ¨
    0.08
     transfer
    0.08
    transfer
    0.08
    ä¸īéĥ¨æĽ²
    0.07
     Correct
    0.07
    äºĶåij³
    0.07
    第ä¸Ģ件äºĭ
    0.07
    ampak
    0.07
    Activations Density 0.003%

    No Known Activations