© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37377
    Prev
    Next
    INDEX
    Explanations

    stock market and investors

    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
    åī²
    -0.10
    çļij
    -0.09
    æݢ索
    -0.09
    åŁºæķ°
    -0.09
     reint
    -0.08
    ÑģеÑĢ
    -0.08
    å·´æĭī
    -0.08
    urvey
    -0.08
    ãĥ³ãĥĪ
    -0.08
    _Metadata
    -0.08
    POSITIVE LOGITS
    èĤ¡ä»·
    0.20
    èĤ¡ç¥¨
    0.15
    èĤ¡å¸Ĥ
    0.14
     stock
    0.12
     Stock
    0.12
    油价
    0.12
    éĩijä»·
    0.12
     STOCK
    0.11
     investors
    0.11
    .stock
    0.11
    Activations Density 0.060%

    No Known Activations