© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 32714
    Prev
    Next
    INDEX
    Explanations

    language understanding

    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
    å¯Ħ
    -0.13
    ä¼ļå½±åĵįåĪ°
    -0.11
    ä¼ļå½±åĵį
    -0.10
    尽快
    -0.10
    çļĦæĦıä¹ī
    -0.10
    æĦıä¹ī
    -0.09
    åħĢ
    -0.09
    abee
    -0.09
    apur
    -0.09
    æ´ĭæ´ĭ
    -0.09
    POSITIVE LOGITS
    ç§ĺè¯Ģ
    0.20
    å¾ĹçĽĬäºİ
    0.18
    è¯Ģ
    0.14
    èĥĮåIJİ
    0.13
    èĥĮåIJİçļĦ
    0.13
    çļĦèĥĮåIJİ
    0.12
    çļĦæĪIJåĬŁ
    0.11
    æĺ¯å¦Ĥä½ķ
    0.11
    éĩĩçĶ¨äºĨ
    0.11
    æĺ¯æĢİä¹Ī
    0.11
    Activations Density 0.157%

    No Known Activations