© 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. 16966
    Prev
    Next
    INDEX
    Explanations

    currency, quantities, and price

    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
    亿åIJ¨
    -0.08
    å¯Ĩ
    -0.07
    ijo
    -0.07
    ooks
    -0.06
    atars
    -0.06
    ä¸Ģç§Ĵ
    -0.06
    åħĥçİ°éĩij
    -0.06
    -scale
    -0.06
     Jog
    -0.06
     uncon
    -0.06
    POSITIVE LOGITS
     price
    0.09
    price
    0.08
     prices
    0.08
    ä¸Ĭ涨äºĨ
    0.08
     priced
    0.08
    大æ´ĭ
    0.08
    Disposition
    0.08
    åħĥèµ·
    0.08
     waived
    0.07
    ersistence
    0.07
    Activations Density 0.167%

    No Known Activations