© 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. 51921
    Prev
    Next
    INDEX
    Explanations

    pretty much

    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
    ç«ŁçĦ¶
    -0.11
    ä½łè§īå¾Ĺ
    -0.10
    æ³ī
    -0.10
    Subview
    -0.10
    otal
    -0.10
    çĶļèĩ³è¿ŀ
    -0.09
    ç®Ģ缴æĺ¯
    -0.09
    æī¼
    -0.09
    æĹłä¸į
    -0.09
    ä¸įè§ģ
    -0.09
    POSITIVE LOGITS
    инÑĭ
    0.09
    æİĮæı¡
    0.09
    æİĮæı¡äºĨ
    0.09
    åģľçķĻåľ¨
    0.09
    宣åijĬ
    0.08
    ëĮĢë¡ľ
    0.08
    mers
    0.08
    ing
    0.08
    cken
    0.08
    town
    0.08
    Activations Density 0.003%

    No Known Activations