© 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. 3267
    Prev
    Next
    INDEX
    Explanations

    archives and publications

    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
    tent
    -0.25
    ude
    -0.25
    æī¿åıĹ
    -0.24
    èĢ¦
    -0.24
    uden
    -0.23
    å¤Ħ
    -0.21
    çİĦ
    -0.21
    大èĩªçĦ¶
    -0.21
    壳
    -0.21
     hat
    -0.21
    POSITIVE LOGITS
     archives
    0.36
     archive
    0.30
    -archive
    0.29
     newspapers
    0.29
    æ£Ģç´¢
    0.27
     Archive
    0.27
    Archive
    0.25
     archival
    0.25
    åı²æĸĻ
    0.25
    æĬ¥ä¸ļ
    0.24
    Activations Density 0.007%

    No Known Activations