© 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. 20608
    Prev
    Next
    INDEX
    Explanations

    one of the

    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
    ooter
    -0.10
    è¿Ļä¹Łæĺ¯
    -0.10
    ãģĵãĤĮãģ¯
    -0.10
    å¼Ģå¥ĸ
    -0.09
    çļĦæĸĩåĮĸ
    -0.09
    çĥ«
    -0.09
     неÑĤ
    -0.09
    ase
    -0.09
    asing
    -0.09
    .Broadcast
    -0.09
    POSITIVE LOGITS
    èİ«è¿ĩäºİ
    0.15
    åľ¨äºİ
    0.11
    ä½Ĩä¸įéĻIJäºİ
    0.11
    è¦ģæĬĬ
    0.10
    èµ°åľ¨
    0.10
    çļĦåĪ°æĿ¥
    0.09
    大夫
    0.09
    æĿ¥èĩªäºİ
    0.09
    ä»Ģä¹Īåij¢
    0.09
     Consort
    0.09
    Activations Density 0.147%

    No Known Activations