© 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. 3199
    Prev
    Next
    INDEX
    Explanations

    yards, statistics

    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
    forge
    -0.29
    tape
    -0.25
    ych
    -0.23
    ç¾½æ¯Ľ
    -0.22
    éĴı
    -0.22
     Briggs
    -0.22
    Éĵ
    -0.22
    YG
    -0.22
    holder
    -0.22
    çĤ¼
    -0.21
    POSITIVE LOGITS
    è¸ı
    0.28
    èµ°å¾Ĺ
    0.25
    æ¯Ķ
    0.24
    ç®ķ
    0.24
    å§Ķ
    0.23
     transmission
    0.23
    detect
    0.22
     underground
    0.22
    é¼ł
    0.21
    ียม
    0.21
    Activations Density 0.002%

    No Known Activations