© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 3280
    Prev
    Next
    INDEX
    Explanations

    -minded, -ness, -ful, -ic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    æ¥Ķ
    -0.23
    asca
    -0.22
     deceptive
    -0.21
     brokerage
    -0.21
    ắt
    -0.21
    æ¾Ħ
    -0.20
    éĢ¼è¿ij
    -0.20
    åIJĦ项
    -0.20
    (arc
    -0.20
     opaque
    -0.20
    POSITIVE LOGITS
     minded
    0.28
    æĥ³çŁ¥éģĵ
    0.28
    -minded
    0.26
    åįģ足
    0.24
    ä¸Ģç§Ĵ
    0.24
     дÑĥÑħ
    0.23
    主任
    0.23
     incarn
    0.23
    Roy
    0.23
    /stat
    0.23
    Activations Density 0.053%

    No Known Activations