© 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. 47890
    Prev
    Next
    INDEX
    Explanations

    start or begin

    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
    åħ¶å®ĥéĹ®é¢ĺ
    -0.10
    itzer
    -0.10
    åģľä¸ĭæĿ¥
    -0.10
    æ¯ıä¸Ģ次
    -0.10
    ä¸ĢæŶ
    -0.10
    лиз
    -0.10
    çļĦ缮åħī
    -0.09
    ä¸Ģçľ¼
    -0.09
    QL
    -0.09
    人士
    -0.09
    POSITIVE LOGITS
    æŃ£å¼ı
    0.10
     formal
    0.10
     actual
    0.09
    è®Ń
    0.08
    chl
    0.08
    ä¸įä¹ħ
    0.08
    äºĨèµ·æĿ¥
    0.08
    äºĨåIJĹ
    0.08
    iec
    0.08
     execution
    0.08
    Activations Density 0.065%

    No Known Activations