© 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. 21912
    Prev
    Next
    INDEX
    Explanations

    not 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
    æ·±åıĹ
    -0.10
    è¿Ļæīį
    -0.09
    à¤ŀ
    -0.09
    åIJ¾
    -0.09
    æĹłè®ºæĺ¯
    -0.09
    ढ
    -0.08
    æľīå¿ħè¦ģ
    -0.08
    æĹłå¿§
    -0.08
     LCS
    -0.08
    æĦŁè§¦
    -0.08
    POSITIVE LOGITS
    æĻ®éĢļçļĦ
    0.12
    èĢĮæĺ¯
    0.11
    éļı便
    0.11
    æĻ®éĢļ
    0.10
    ä»»æĦı
    0.10
     ordinary
    0.10
     merely
    0.10
    寻常
    0.09
    ordinary
    0.09
     обÑĭÑĩ
    0.09
    Activations Density 0.040%

    No Known Activations