© 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. 26299
    Prev
    Next
    INDEX
    Explanations

    bus or buses

    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
    稷
    -0.12
    çŁ¿ä¸ļ
    -0.10
    èĩ³å°Ĭ
    -0.10
    妻
    -0.10
    ç¬Ļ
    -0.09
     Meyer
    -0.09
    让åŃ©åŃIJ
    -0.09
    ITED
    -0.09
    rijk
    -0.09
    åľ°å¸¦
    -0.09
    POSITIVE LOGITS
     bus
    0.11
    bus
    0.10
     buses
    0.10
    Bus
    0.09
    tip
    0.09
    ä¹ĺ客
    0.09
    è¿IJèIJ¥
    0.09
    ä¸įåĪ°
    0.09
    çĭŃ
    0.09
    .bi
    0.09
    Activations Density 0.095%

    No Known Activations