© 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. 40135
    Prev
    Next
    INDEX
    Explanations

    departure and arrival locations

    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
    é»ĺ
    -0.11
    éļį
    -0.10
    黾
    -0.10
    æ´»å¾Ĺ
    -0.09
    é¢Ĩ
    -0.09
    æѤ类
    -0.09
    çķ°
    -0.09
    è§Ħ磩
    -0.09
    æŀŃ
    -0.08
    尽头
    -0.08
    POSITIVE LOGITS
    åĩºåıij
    0.15
    太
    0.10
    æºIJ
    0.09
    彦
    0.08
     groom
    0.08
    åľ¨åĵªéĩĮ
    0.08
    ä¸įä¹ħ
    0.08
    çĤ¹
    0.08
    ittal
    0.08
    iah
    0.08
    Activations Density 0.054%

    No Known Activations