© 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. 1214
    Prev
    Next
    INDEX
    Explanations

    accounting and finance

    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
    elum
    -0.07
    ifu
    -0.07
     particol
    -0.07
    éĢłæĪIJ伤害
    -0.07
    åħĭå°Ķ
    -0.07
    æĶ¿åĬ¡æľįåĬ¡
    -0.07
     Rappel
    -0.07
    èݽ
    -0.07
    ewis
    -0.07
    anford
    -0.07
    POSITIVE LOGITS
    æĬ¥è¡¨
    0.12
    /account
    0.11
    æł¸ç®Ĺ
    0.11
     Accounting
    0.11
    è®°è´¦
    0.10
     бÑĥÑħгалÑĤеÑĢ
    0.10
    ç°¿
    0.10
     auditing
    0.10
     accounting
    0.10
    ä¼ļ计
    0.10
    Activations Density 0.151%

    No Known Activations