© 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. 26219
    Prev
    Next
    INDEX
    Explanations

    cable television and networks

    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
    qli
    -0.10
     latter
    -0.10
    è´§æŀ¶
    -0.09
    为主é¢ĺçļĦ
    -0.09
    atur
    -0.09
    ibus
    -0.09
    sole
    -0.09
    esse
    -0.09
    åIJİèĢħ
    -0.09
    大è±Ĩ
    -0.09
    POSITIVE LOGITS
    人身
    0.08
    äººæł¼
    0.08
    aber
    0.08
    -Feb
    0.08
    巨头
    0.08
    èµ¢å¾Ĺ
    0.08
    è¿ĩå¹´
    0.08
    殳
    0.08
    æĶ¾æĿ¾
    0.07
    çķĮçļĦ
    0.07
    Activations Density 0.011%

    No Known Activations