© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 47659
    Prev
    Next
    INDEX
    Explanations

    from scratch or from the ground up

    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
    Negative Logits
    ä¸įä¸ĭ
    -0.10
    blend
    -0.09
    اÙģت
    -0.09
    nist
    -0.09
    à¸Ńร
    -0.08
    Whats
    -0.08
    orical
    -0.08
    æĹĨ
    -0.08
    åĸĺ
    -0.08
    ä¸įä¸Ĭ
    -0.08
    POSITIVE LOGITS
    ilers
    0.10
    lings
    0.09
    warn
    0.09
    åıĪæĺ¯
    0.09
    宥
    0.09
    /random
    0.08
    ãģ¨è¨Ģãģ£ãģ¦
    0.08
    æĭĪ
    0.08
    æĶ¾æīĭ
    0.08
    ä¸Ģçīĩ
    0.08
    Activations Density 0.010%

    No Known Activations