© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2773
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
    /fa
    -0.24
    æķ´ä¸ªäºº
    -0.24
    enate
    -0.24
    èľ¿
    -0.23
    éļĨéĩį
    -0.22
     капиÑĤал
    -0.22
    èĸĦèĨľ
    -0.22
    éĩįç£ħ
    -0.22
    纪念ç¢ij
    -0.22
     leaps
    -0.22
    POSITIVE LOGITS
    åħ¥ä½ı
    0.31
    åģļé¥Ń
    0.25
    ä½ı宿
    0.24
     bathrooms
    0.23
     Prep
    0.23
    æĪ·ç±į
    0.23
    客
    0.23
     backtrack
    0.23
     hotel
    0.22
     gag
    0.22
    Activations Density 0.003%

    No Known Activations