© 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. 10553
    Prev
    Next
    INDEX
    Explanations

    prizes, items, and rewards

    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
    amb
    -0.21
    омеÑĢ
    -0.20
    éķľåŃIJ
    -0.18
    ÑıÑģ
    -0.18
    BIN
    -0.18
    ÑĢей
    -0.17
    ëĭ¤ë©´
    -0.17
    миÑĢ
    -0.17
    åħ±æĮ¯
    -0.17
    ensive
    -0.17
    POSITIVE LOGITS
    ä¸ºæľŁ
    0.25
     spot
    0.23
    æį¢åıĸ
    0.21
    缸è§ģ
    0.21
    åįĩ
    0.20
    éĽĨåĽ¢èĤ¡ä»½
    0.20
    éľģ
    0.19
    è±ģ
    0.19
    å¥ĸåĬ±
    0.19
    ullan
    0.18
    Activations Density 0.086%

    No Known Activations