© 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. 52880
    Prev
    Next
    INDEX
    Explanations

    boycott

    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
    owie
    -0.11
    è¿ĺæľīä¸ĢäºĽ
    -0.11
    åģĥ
    -0.09
    鬻
    -0.09
    åįģå¹´åīį
    -0.09
    第ä¸Ģç«ł
    -0.09
    daq
    -0.08
    ä½łè¿ĺ
    -0.08
    Î
    -0.08
    oved
    -0.08
    POSITIVE LOGITS
    able
    0.10
    å¼ĢéŨ
    0.10
    ably
    0.09
    cks
    0.09
    enance
    0.09
    æĢª
    0.09
    ä¹ı
    0.08
    æ®Ĩ
    0.08
    .blank
    0.08
    æİīäºĨ
    0.08
    Activations Density 0.009%

    No Known Activations