© 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. 3310
    Prev
    Next
    INDEX
    Explanations

    He just

    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
    .tip
    -0.24
    樽
    -0.22
    bons
    -0.22
    éĺ»æĮ¡
    -0.22
     minded
    -0.22
    ĥĿ
    -0.21
    å¼ĢèĬ±
    -0.21
     fur
    -0.21
     blasph
    -0.21
    æ·«
    -0.21
    POSITIVE LOGITS
    yz
    0.24
     Sm
    0.22
    åĿ¦
    0.22
     upon
    0.22
    SMART
    0.22
    èĽŃ
    0.22
     DOT
    0.22
    uating
    0.21
     æĸ
    0.21
     inclusive
    0.20
    Activations Density 0.172%

    No Known Activations