© 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. 6167
    Prev
    Next
    INDEX
    Explanations

    travel and fares

    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
    åģľè½¦åľº
    -0.12
    cord
    -0.11
    æī«
    -0.10
    æݥ管
    -0.10
    æ¡¢
    -0.10
    zin
    -0.10
    çĶ¸
    -0.10
    ãĤ·ãĥ§ãĥ³
    -0.09
    屯
    -0.09
    çŁ¥è¯ĨçĤ¹
    -0.09
    POSITIVE LOGITS
    æľºç¥¨
    0.15
    èµ´
    0.12
    èĪªçıŃ
    0.12
     voyage
    0.12
    å¾Ģè¿Ķ
    0.12
    æĹħè¡Į
    0.12
     trip
    0.12
     travel
    0.11
    âľĪ
    0.11
     trips
    0.11
    Activations Density 0.071%

    No Known Activations