© 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. 37429
    Prev
    Next
    INDEX
    Explanations

    large/massive/big/major [quantity/scope]

    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
    æĤ¨çļĦåŃ©åŃIJ
    -0.09
    åĭ¤å¥ĭ
    -0.08
    _codec
    -0.08
    åĩ¤åĩ°
    -0.08
    sockets
    -0.08
     Spo
    -0.08
    æ¯ıæ¯ı
    -0.08
    rez
    -0.08
    codec
    -0.08
    èĤ©èĨĢ
    -0.08
    POSITIVE LOGITS
    éĩijéĴ±
    0.09
    alous
    0.08
    enary
    0.08
    迸
    0.08
    ebra
    0.08
    ä¸Ģ次æĢ§
    0.08
    åľĪåŃIJ
    0.08
    大夫
    0.08
    æĬ½
    0.08
    etary
    0.08
    Activations Density 0.097%

    No Known Activations