© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7572
    Prev
    Next
    INDEX
    Explanations

    comparing to

    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
    ä¸Ģ缴
    -0.09
    ãĤ·ãĥ¼
    -0.09
    æīįæĺ¯
    -0.09
    æĶ¾åѦ
    -0.09
    åĦ¿
    -0.09
    ä¸ĢåIJij
    -0.09
    æĢİä¹Īåģļ
    -0.09
    obot
    -0.09
     XK
    -0.08
    ardin
    -0.08
    POSITIVE LOGITS
     compared
    0.33
    缸æ¯Ķ
    0.29
    çĽ¸å¯¹äºİ
    0.27
    缸æ¯Ķäºİ
    0.26
    缸è¾ĥäºİ
    0.25
     Compared
    0.23
    缸è¾ĥ
    0.22
    æ¯Ķèµ·
    0.21
    æ¯Ķãģ¹
    0.18
    缸æ¯Ķä¹ĭä¸ĭ
    0.17
    Activations Density 0.281%

    No Known Activations