© 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. 26106
    Prev
    Next
    INDEX
    Explanations

    direction, destination, or location

    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
    æĶ¸
    -0.09
    bable
    -0.09
    åĩĽ
    -0.09
    æĻ¯å¾·
    -0.08
    ä¸Ńå°ı
    -0.08
    å±Ĥå±Ĥ
    -0.08
     اÙĦشرÙĬÙģ
    -0.08
    à¹ģà¸ģ
    -0.08
    ç»Ħç»ĩå®ŀæĸ½
    -0.08
    æ¼ı
    -0.08
    POSITIVE LOGITS
    åIJŁ
    0.10
    æĸ¹åIJij
    0.09
    æŶå°ļ
    0.09
    ä½İè°ĥ
    0.09
    Directions
    0.08
    est
    0.08
     directions
    0.08
    ä¸įæľį
    0.08
     direction
    0.08
    å¬ī
    0.08
    Activations Density 0.083%

    No Known Activations