© 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. 51898
    Prev
    Next
    INDEX
    Explanations

    duration of day

    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
    izoph
    -0.10
    apsed
    -0.10
     Nights
    -0.10
    åįĬæľĪ
    -0.09
    esz
    -0.09
    è°¶
    -0.09
    .ma
    -0.09
    åĿļ强
    -0.09
    èĥĦ
    -0.09
    hausen
    -0.09
    POSITIVE LOGITS
    åĮĹ京大åѦ
    0.10
    åĤ¬
    0.09
    ../
    0.09
    ronic
    0.09
    åIJĦ个æĸ¹éĿ¢
    0.08
    ree
    0.08
    æ±ģ
    0.08
    ../../
    0.08
    ä¸Ĭä¸ĭ
    0.08
    æݨ广åºĶçĶ¨
    0.08
    Activations Density 0.011%

    No Known Activations