© 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. 8169
    Prev
    Next
    INDEX
    Explanations

    academic subjects or degrees earned

    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
    失
    -0.09
    åħ±è¯Ĩ
    -0.09
    éĩĬ
    -0.09
    ç³»åĪĹæ´»åĬ¨
    -0.08
    åįĥä¸ĩ
    -0.08
    èĢĮå·²
    -0.08
    çݯ氧
    -0.08
    ilar
    -0.08
    篱
    -0.08
    çݯä¿Ŀ
    -0.08
    POSITIVE LOGITS
    çī¹åĪ«å£°æĺİ
    0.11
    æĪIJ为ä¸ĢåIJį
    0.10
    ä½Ĩä»İ
    0.09
    æ¯ķä¸ļäºİ
    0.09
    ç°ĩ
    0.09
    è·
    0.09
    orte
    0.09
    çĶŁäºİ
    0.08
     Oc
    0.08
    身ä½ĵåģ¥åº·
    0.08
    Activations Density 0.059%

    No Known Activations