© 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. 51605
    Prev
    Next
    INDEX
    Explanations

    reported events

    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
    åij¨æľŁ
    -0.09
    åĪ¤
    -0.09
    icter
    -0.09
    宣åijĬ
    -0.09
    çļ±çº¹
    -0.09
    åĸŁ
    -0.09
    沤
    -0.09
    æİ¥åĪ°
    -0.08
    orda
    -0.08
    æĥľ
    -0.08
    POSITIVE LOGITS
    并ä¸İ
    0.09
    ä¸įåģľåľ°
    0.09
    è§
    0.09
    ysi
    0.09
    èijij
    0.08
    å¾Ģå¤ĸ
    0.08
    æ±ķ
    0.08
    ÑģÑĤоÑı
    0.08
    è¯¥æł¡
    0.08
    sic
    0.08
    Activations Density 0.038%

    No Known Activations