© 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. 720
    Prev
    Next
    INDEX
    Explanations

    used as or for

    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
    åįĩèµ·
    -0.09
    Fabric
    -0.08
     elim
    -0.08
    好è¿IJ
    -0.08
    çĶ°åĽŃ
    -0.08
    çľĭäºĨä¸Ģ
    -0.08
    æīĢéľĢ
    -0.07
    à²Ł
    -0.07
    æľīåĬ©
    -0.07
    ncy
    -0.07
    POSITIVE LOGITS
    ä¸ĸçķĮåIJĦåľ°
    0.10
    åľ¨æĹ¥æľ¬
    0.10
    VOKE
    0.10
    åľ¨è¿ĩ渡
    0.10
     ë§İìĿ´
    0.09
    å®ŀè·µä¸Ń
    0.09
    åģļä¸ĢäºĽ
    0.09
    åľ¨ä¸ŃåĽ½
    0.09
    boro
    0.09
    å¹¿æ³Ľ
    0.09
    Activations Density 0.358%

    No Known Activations