© 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. 5027
    Prev
    Next
    INDEX
    Explanations

    Framework, Inc., Alban, purpose

    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
    建
    -0.09
    ilion
    -0.09
    宽æĿ¾
    -0.08
    æģķ
    -0.08
    lle
    -0.08
    åĥµ
    -0.08
    å¾Īæĺİæĺ¾
    -0.08
    lee
    -0.08
    å°ıå°ı
    -0.08
    loc
    -0.08
    POSITIVE LOGITS
    æĤ¬
    0.10
    çºł
    0.10
    gress
    0.09
    ä¼łç»Łäº§ä¸ļ
    0.09
    éģĹæ¼ı
    0.09
    gres
    0.09
    SA
    0.09
    utches
    0.08
    Powered
    0.08
    åĭ¤å¥ĭ
    0.08
    Activations Density 0.001%

    No Known Activations