© 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. 31925
    Prev
    Next
    INDEX
    Explanations

    fake hair or instant celebrity

    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
    åŁł
    -0.10
    æľīè¶³å¤ŁçļĦ
    -0.10
    å°ı女åŃ©
    -0.09
    è·¨çķĮ
    -0.09
    åı¤èĢģçļĦ
    -0.09
    å¿ĥ缮
    -0.09
    å¾Īæ£Ĵ
    -0.09
    æľīè¿Ļæł·çļĦ
    -0.09
    åı¤èĢģ
    -0.08
    å°ıå§IJå§IJ
    -0.08
    POSITIVE LOGITS
     ones
    0.15
     stuff
    0.12
    为主çļĦ
    0.10
    å¾Ģå¾Ģ
    0.09
    èĢĮæĺ¯
    0.09
    IPP
    0.09
    æĹłç¼ĺ
    0.09
     Stuff
    0.09
    æĪijä»¬åľ¨
    0.08
    ones
    0.08
    Activations Density 0.121%

    No Known Activations