© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 17296
    Prev
    Next
    INDEX
    Explanations

    limited editions and runs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    çĶŁæĹ¥
    -0.19
    ä¸į论æĺ¯
    -0.19
     Downs
    -0.19
    ä¸įä½Ĩ
    -0.18
    mina
    -0.18
    WithEmail
    -0.17
    äºĨåIJĹ
    -0.17
    碰åĪ°
    -0.17
    æ£Ģ
    -0.17
    åĩ¡æĺ¯
    -0.17
    POSITIVE LOGITS
    æĥħåĨµè¿Ľè¡Į
    0.24
    éĻIJéĩı
    0.22
    éĻIJæŶ
    0.18
    衾
    0.18
    çī¹éĤĢ
    0.18
    éŃĶçİĭ
    0.18
    èĬĹ
    0.18
    ipop
    0.18
    auce
    0.17
     cấp
    0.17
    Activations Density 0.006%

    No Known Activations