© 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. 48754
    Prev
    Next
    INDEX
    Explanations

    causes things to happen

    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
     ÑģÑĤала
    -0.09
     ÑģоÑħÑĢани
    -0.09
    常çĶ¨
    -0.09
    å·¥ä½ľå®¤
    -0.08
    举æĬ¥
    -0.08
    å¼ķèµ·äºĨ
    -0.08
    æµ·è¿IJ
    -0.08
     hers
    -0.08
    avad
    -0.08
    æĬķè¯ī
    -0.08
    POSITIVE LOGITS
    æīįæľī
    0.10
    åĬ¿
    0.10
    ä¼ĹæīĢ
    0.09
    人们
    0.09
    æį
    0.09
    人们对
    0.09
    ä¸įäºĨ
    0.09
    ä¸įä»ħèĥ½
    0.09
     excess
    0.09
    æĺ¯æľī
    0.09
    Activations Density 0.146%

    No Known Activations