© 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. 3370
    Prev
    Next
    INDEX
    Explanations

    comfortable discussing, using, giving, writing

    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
    coop
    -0.26
    brane
    -0.24
    Forgot
    -0.24
    coh
    -0.24
    æĭĽèģĺä¿¡æģ¯
    -0.22
    dal
    -0.22
    dl
    -0.22
    åIJ¬èµ·æĿ¥
    -0.22
     fortunes
    -0.22
    eprom
    -0.21
    POSITIVE LOGITS
     comfortable
    0.32
    èĩªå¦Ĥ
    0.31
    èĩªåľ¨
    0.29
     confident
    0.29
    驾é©Ń
    0.28
     confidence
    0.26
    ä¸İåIJ¦
    0.25
     familiarity
    0.24
     comfortably
    0.24
     uncomfortable
    0.24
    Activations Density 0.018%

    No Known Activations