© 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. 39166
    Prev
    Next
    INDEX
    Explanations

    generally, mostly, typically

    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
    lessly
    -0.12
    ARAM
    -0.09
     jä
    -0.09
    ä¸ĵåijĺ
    -0.09
    éģįåıĬ
    -0.09
    äº¤æĽ¿
    -0.09
    æĮģå¹³
    -0.09
    æĦıæĥ³ä¸įåĪ°
    -0.09
    ELY
    -0.09
    å¦ĤæĦı
    -0.09
    POSITIVE LOGITS
    å¾Ī好
    0.09
    说çļĦè¯Ŀ
    0.09
    ä¸įæķ¢
    0.09
    cation
    0.08
     Glo
    0.08
    æĺ¯æľĢ
    0.08
    _quick
    0.07
    าย
    0.07
    DES
    0.07
    opic
    0.07
    Activations Density 0.086%

    No Known Activations