© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 23804
    Prev
    Next
    INDEX
    Explanations

    one or two

    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
    å¾Ĵ
    -0.09
     Harding
    -0.08
     convention
    -0.08
    æĤĸ
    -0.08
    eware
    -0.08
    æĶĢåįĩ
    -0.08
    зв
    -0.08
     commerce
    -0.08
     bol
    -0.08
    agra
    -0.08
    POSITIVE LOGITS
    åIJĦæł·
    0.15
    æĪĸå¤ļæĪĸå°ij
    0.12
    ä¹Łå¥½
    0.11
    ëĵł
    0.11
    è¿ĺæĺ¯
    0.11
     or
    0.10
    ä¸İåIJ¦
    0.10
    æĪĸå¤ļæĪĸ
    0.10
    -or
    0.10
    åIJĦç§į
    0.10
    Activations Density 0.047%

    No Known Activations