© 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. 21917
    Prev
    Next
    INDEX
    Explanations

    not, 't, and just

    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¸įå°ı
    -0.12
    ä¸įæľį
    -0.11
    å¯Ŀ
    -0.11
    ä¸įå¤Ł
    -0.11
    ä¸įå°ıçļĦ
    -0.11
    ä¸įå°ij
    -0.10
    ä¸įéĶĻ
    -0.10
    å¾Īéķ¿
    -0.10
    ä¸įèĤ¯
    -0.10
    èĬĤ
    -0.09
    POSITIVE LOGITS
    éĤ£ä¹Īå¤ļ
    0.15
    æ¯ı次éĥ½
    0.12
    è¿Ļä¹Īå¤ļ
    0.12
    éĤ£ä¹Ī容æĺĵ
    0.11
    éĤ£ä¹Ī
    0.11
    ä¸Ģä¸ĭåŃIJå°±
    0.10
    ä¾Ŀèµĸ
    0.10
    å¦ĤæѤ
    0.10
    éĤ£éº¼
    0.10
     anymore
    0.09
    Activations Density 0.121%

    No Known Activations