© 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. 48453
    Prev
    Next
    INDEX
    Explanations

    Bloomberg and financial news

    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
    å°ĨåĨĽ
    -0.10
    åºķéĥ¨
    -0.09
    æī£éĻ¤
    -0.08
    fort
    -0.08
    æ²Ł
    -0.08
    atorium
    -0.08
    è¿ĩé«ĺ
    -0.08
    è¿ĩåĪĨ
    -0.08
    ç»ļ丽
    -0.08
    inte
    -0.08
    POSITIVE LOGITS
    é«ĺé¢ij
    0.10
    اÙĪ
    0.10
    大å®ĹåķĨåĵģ
    0.10
    å¾ĭ
    0.10
    SETS
    0.09
    åļ¼
    0.09
    èŤ
    0.09
     Bloomberg
    0.09
    ä¸ŃåĽ½ç»ıæµİ
    0.08
    plib
    0.08
    Activations Density 0.027%

    No Known Activations