© 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. 16585
    Prev
    Next
    INDEX
    Explanations

    thinking about

    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
    çľĭä¸įæĩĤ
    -0.11
    æĺ¯ä»Ģä¹Īåij¢
    -0.09
     halftime
    -0.08
    çļĦæīĭ
    -0.08
    arin
    -0.08
    åİŁå§ĭ
    -0.08
    çĵ¶
    -0.08
    éĽī
    -0.08
    è¿Ļåıªæĺ¯
    -0.08
    èµ·æĿ¥äºĨ
    -0.08
    POSITIVE LOGITS
    æıIJåıĬ
    0.16
    è¿Ļ个åIJįåŃĹ
    0.14
     mention
    0.14
    æĥ³èµ·
    0.14
    æıIJèµ·
    0.14
    æĥ³åĪ°
    0.13
    è°ĪåıĬ
    0.13
     Mention
    0.12
    è°Ī论
    0.12
     mentioning
    0.12
    Activations Density 0.073%

    No Known Activations