© 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. 37528
    Prev
    Next
    INDEX
    Explanations

    FOR IMMEDIATE RELEASE or PUBLICATION

    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
    å¼ĤæĢ§
    -0.09
    ever
    -0.09
    åĬ¨æīĭ
    -0.08
    æĶ¶åĪ°äºĨ
    -0.08
    èĪī
    -0.08
    ä»ĸæĽ¾
    -0.08
    èĢĹ
    -0.08
    责任åĪ¶
    -0.08
    åĪĽéĢłäºĨ
    -0.08
    iance
    -0.08
    POSITIVE LOGITS
    íĥij
    0.09
    itas
    0.09
    publication
    0.08
    yyyy
    0.08
    çĮ®
    0.08
     ÑģообÑī
    0.08
    Publication
    0.08
    inges
    0.08
    è°Ł
    0.08
    è¾ĩ
    0.08
    Activations Density 0.011%

    No Known Activations