© 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. 6133
    Prev
    Next
    INDEX
    Explanations

    movement or progression

    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
    ç¡IJ
    -0.10
    åģĮ
    -0.10
    çĶŁäº§å·¥èīº
    -0.10
    ä¸Ģè¶Ł
    -0.09
    æıĨ
    -0.09
    ä¿¡å¿ĥ
    -0.09
    é¼ĭ
    -0.09
    mach
    -0.08
    ä¸ĢåĪĩéĥ½
    -0.08
    åħ¨ç¨ĭ
    -0.08
    POSITIVE LOGITS
    edList
    0.09
    åĢŁçĶ¨
    0.09
    åħ¶å®ĥéĹ®é¢ĺ
    0.09
     Bryan
    0.09
    coh
    0.08
    è¤Ĵ
    0.08
    ä¸ĭä¸Ģ个
    0.08
     into
    0.08
    eing
    0.08
    into
    0.08
    Activations Density 0.023%

    No Known Activations