© 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. 3241
    Prev
    Next
    INDEX
    Explanations

    rotary and constructive criticism

    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
    åľ¨åºĬä¸Ĭ
    -0.23
    åĽ½æ°ijç»ıæµİ
    -0.22
    ddy
    -0.22
    çĿ¡
    -0.21
    arie
    -0.21
    ä¿©
    -0.21
    åŃĽ
    -0.21
    åħ¨éĿ¢å»ºæĪIJ
    -0.21
    æŃ£å¸¸ä½¿çĶ¨
    -0.20
    Ñģо
    -0.20
    POSITIVE LOGITS
    æĶ¯æĮģ
    0.26
    缸åĬ©
    0.23
     support
    0.22
     assistance
    0.21
    anson
    0.21
     Emin
    0.20
     Hour
    0.20
     increment
    0.20
     sectors
    0.20
     Day
    0.20
    Activations Density 0.003%

    No Known Activations