© 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. 40355
    Prev
    Next
    INDEX
    Explanations

    not seek

    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
    IVES
    -0.09
    æľīçĶ¨
    -0.09
    oled
    -0.09
    æľį
    -0.08
    ä¸įèĥ½
    -0.08
    (binding
    -0.08
    ä¸įå¾Ĺä¸į
    -0.08
     зÑĢ
    -0.08
    .typ
    -0.08
    жа
    -0.08
    POSITIVE LOGITS
     anymore
    0.12
    åıĤ
    0.10
    追究
    0.09
    åĨįåİ»
    0.09
    æī©å¤§
    0.09
     opposite
    0.09
    ä»Ĭå¹´
    0.08
    å°Ĩ继ç»Ń
    0.08
    Growing
    0.08
    ä¸Ŀ毫
    0.08
    Activations Density 0.067%

    No Known Activations