© 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. 3418
    Prev
    Next
    INDEX
    Explanations

    degree from or in

    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
     Äijỡ
    -0.20
    æĹ¥å¸¸çĶŁæ´»
    -0.20
    æĪı
    -0.20
    ä¼ļè§īå¾Ĺ
    -0.19
    autoload
    -0.19
    ergic
    -0.19
    è§ħ
    -0.19
    æĥ³æĥ³
    -0.19
    ä¸įå®ļ
    -0.19
    _DECLS
    -0.19
    POSITIVE LOGITS
    erate
    0.24
     holders
    0.23
    ed
    0.23
    arten
    0.22
    veloper
    0.21
     holder
    0.21
     Celsius
    0.21
     from
    0.21
    e
    0.21
    naire
    0.20
    Activations Density 0.015%

    No Known Activations