© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 48832
    Prev
    Next
    INDEX
    Explanations

    stock price movement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    жи
    -0.09
    éªĽ
    -0.09
    _SER
    -0.08
     mar
    -0.08
    è¢ĭ
    -0.08
    .mar
    -0.08
    å¼Ĥè®®
    -0.08
    anmar
    -0.08
    çĸijæĥij
    -0.08
     Bett
    -0.08
    POSITIVE LOGITS
    ä»·æł¼ä¸Ĭ涨
    0.16
     prices
    0.13
    ä»·æł¼
    0.13
    å¸Ĥåľºä»·æł¼
    0.11
    ä»·éĴ±
    0.11
    prices
    0.11
     Prices
    0.11
    åıĮåıĮ
    0.11
    èĤ¡ä»·
    0.11
    éĩijä»·
    0.11
    Activations Density 0.113%

    No Known Activations