© 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. 29632
    Prev
    Next
    INDEX
    Explanations

    increase or double

    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
    涣
    -0.10
    çİ°å·²
    -0.10
    ä½Ĩçİ°åľ¨
    -0.09
    éĢłåŀĭ
    -0.08
    峤
    -0.08
    è¾¹
    -0.08
    ãĤ¤ãĤ¹
    -0.08
     dest
    -0.08
    onym
    -0.08
    强åĪ¶
    -0.08
    POSITIVE LOGITS
    缸åºĶ
    0.13
    缸åºĶçļĦ
    0.13
    éļıä¹ĭ
    0.13
    åIJĮæŃ¥
    0.12
    ä¸İæѤåIJĮæŶ
    0.11
    ä¹Łéļıä¹ĭ
    0.10
    没åħ³ç³»
    0.10
    çĻĸ
    0.10
    ä¸įåıĺ
    0.10
    ä¼´
    0.09
    Activations Density 0.311%

    No Known Activations