© 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. 3279
    Prev
    Next
    INDEX
    Explanations

    Infernal Affairs, Shaggy Dog

    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
    éĴ¢åİĤ
    -0.24
    /Library
    -0.23
     fus
    -0.22
    å¼¹
    -0.22
    idan
    -0.22
    弦
    -0.22
     Astroph
    -0.21
    <Card
    -0.21
    nic
    -0.21
    arium
    -0.21
    POSITIVE LOGITS
    æ¯Ĵåĵģ
    0.26
    çĬ¯ç½ª
    0.26
     narcotics
    0.26
    ç¦ģæ¯Ĵ
    0.26
    å··
    0.26
    æĪĴ
    0.25
    ä¿©
    0.23
     tiger
    0.23
    èĻİ
    0.23
     Psy
    0.23
    Activations Density 0.013%

    No Known Activations