© 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. 3270
    Prev
    Next
    INDEX
    Explanations

    unsupported browser or javascript

    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
    éĻĦå±ŀ
    -0.26
    è´¯éĢļ
    -0.25
    èģĶåĬ¨
    -0.24
    éĻĦ件
    -0.23
    Listeners
    -0.23
    ýt
    -0.23
    æŀIJ
    -0.23
    æķij人
    -0.22
    locate
    -0.22
    åĮħ
    -0.22
    POSITIVE LOGITS
    _browser
    0.30
     javascript
    0.28
    /javascript
    0.28
    -ish
    0.28
     browser
    0.27
    æľ¬ç½ij
    0.26
     toolbar
    0.24
     website
    0.24
    -esque
    0.24
    åı¯ä»¥æĽ´å¥½
    0.24
    Activations Density 0.039%

    No Known Activations