© 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. 779
    Prev
    Next
    INDEX
    Explanations

    to or for someone

    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
    ä¼ļ让
    -0.10
    对åħ¶çľŁå®ŀ
    -0.09
    åıĮèħ¿
    -0.09
    å¾Ī大ç¨ĭ度
    -0.09
    让å®ĥ
    -0.09
    åħĢ
    -0.09
    请大家
    -0.08
    éŨåīį
    -0.08
    zilla
    -0.08
    çĿĢä»ĸ
    -0.08
    POSITIVE LOGITS
    æĿ¥è®²
    0.12
    æĿ¥åģļ
    0.11
    æĿ¥è¯´
    0.11
    ç¦ıç¥ī
    0.10
    æľīåħ´è¶£
    0.10
     to
    0.09
    ä¾Ĩ說
    0.09
    åİ»åģļ
    0.09
     latch
    0.09
    åĪ©çĽĬ
    0.09
    Activations Density 0.091%

    No Known Activations