© 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. 2671
    Prev
    Next
    INDEX
    Explanations

    Now followed by consequence

    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
    é¢Ĩ
    -0.09
     earlier
    -0.09
    缼
    -0.09
    å°¤åħ¶æĺ¯
    -0.09
    åīįä¸ĸ
    -0.09
    è¡£
    -0.09
    çļĦçłĶåıij
    -0.09
    åħĪæĺ¯
    -0.09
    å½ĵä»Ĭ
    -0.09
    å½ĵåĪĿ
    -0.09
    POSITIVE LOGITS
    ually
    0.09
    oger
    0.09
    继
    0.08
    ç¹¼
    0.08
    ä¸ī次
    0.08
    第ä¸ī次
    0.08
    -motion
    0.08
    ä¸ī天
    0.08
    oute
    0.08
    èĥ¡åŃIJ
    0.08
    Activations Density 0.031%

    No Known Activations