© 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. 26655
    Prev
    Next
    INDEX
    Explanations

    market, financial markets, trading, prices

    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
    æĹ¶ä»£ä¸ŃåĽ½
    -0.10
    峪
    -0.10
    pm
    -0.10
    æļ®
    -0.09
    æijĺ
    -0.09
    æį
    -0.08
    åģ·
    -0.08
    æݨä»ĭ
    -0.08
    èĻļ
    -0.08
    è¯ļ
    -0.07
    POSITIVE LOGITS
    å¤ļ人
    0.11
    ä¸Ģ群人
    0.10
    ibur
    0.10
    PTION
    0.10
    广éĺĶ
    0.09
    å°±æĺ¯è¿Ļæł·
    0.09
    æ±
    0.09
    è¶ĭäºİ
    0.09
    èºģ
    0.09
    çĬĩ
    0.09
    Activations Density 0.069%

    No Known Activations