© 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. 8099
    Prev
    Next
    INDEX
    Explanations

    Dow Jones futures

    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
    欺
    -0.09
    èĭ¥æĤ¨
    -0.09
    åŁºæľ¬ä¸Ĭéĥ½
    -0.09
    èĥ¸æĢĢ
    -0.08
    é»ĺ
    -0.08
    ç»įåħ´
    -0.08
    滩
    -0.08
    gone
    -0.08
    æģŃ
    -0.08
    羣è¯ļ
    -0.08
    POSITIVE LOGITS
    PEAT
    0.11
    ä¸īåĽĽ
    0.11
     sup
    0.09
    ç¼ĺ
    0.09
    owe
    0.09
    oland
    0.09
    TÄ°
    0.09
    letters
    0.09
    çĬĬ
    0.09
    doch
    0.09
    Activations Density 0.002%

    No Known Activations