© 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. 17269
    Prev
    Next
    INDEX
    Explanations

    time units and dates

    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
     worlds
    -0.24
     Worlds
    -0.23
     Lau
    -0.20
     Usa
    -0.20
     USA
    -0.20
     Patri
    -0.20
    aat
    -0.19
    çĶ¨åľ°
    -0.19
     cam
    -0.19
    hti
    -0.19
    POSITIVE LOGITS
    -Semit
    0.21
    ç¥
    0.21
     pornost
    0.21
    grave
    0.20
    HandlerContext
    0.20
    è§Ħéģ¿
    0.20
    é¾Ī
    0.20
    ä½Ĩæĺ¯å¦Ĥæŀľ
    0.19
    ä¾ĭãģĪãģ°
    0.19
    æİ£
    0.19
    Activations Density 0.088%

    No Known Activations