© 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. 60264
    Prev
    Next
    INDEX
    Explanations

    financial transaction CONVERT

    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
    ongyang
    -0.08
    _NAMESPACE
    -0.08
    UMMY
    -0.08
    ystone
    -0.08
    uale
    -0.07
    dor
    -0.07
     BSON
    -0.07
    insky
    -0.07
    inale
    -0.07
     Banda
    -0.07
    POSITIVE LOGITS
    ifter
    0.07
    abor
    0.07
    hto
    0.06
    hift
    0.06
    åį³éĢĿ
    0.06
    ader
    0.06
    ýt
    0.06
    adem
    0.06
    ZI
    0.06
    pera
    0.06
    Activations Density 0.851%

    No Known Activations