© 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. 7990
    Prev
    Next
    INDEX
    Explanations

    quarter-finals or semi-finals

    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
    è¾ķ
    -0.09
    æĹĹèĪ°
    -0.09
    oki
    -0.09
    ä¸įæķ¢
    -0.09
    ky
    -0.09
    éĤ£åıª
    -0.08
    ä¸įå¤ļ
    -0.08
    éĩijå¥ĸ
    -0.08
    åĻ¨åħ·
    -0.08
    æŀ·
    -0.08
    POSITIVE LOGITS
    oub
    0.09
    为æŃ¢
    0.09
    èĵģ
    0.09
    /rss
    0.08
    èŀºä¸Ŀ
    0.08
    åı·åı¬
    0.08
    åĵģåij³
    0.08
    éĺ¶æ®µ
    0.08
    rapper
    0.08
    -low
    0.08
    Activations Density 0.028%

    No Known Activations