© 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. 10558
    Prev
    Next
    INDEX
    Explanations

    HEADER

    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
    ka
    -0.20
    EventListener
    -0.20
    LEAN
    -0.19
    kir
    -0.18
    less
    -0.18
    ä¼´
    -0.18
    è¯Ĺè¯į
    -0.18
     [&
    -0.18
    mere
    -0.18
    kc
    -0.17
    POSITIVE LOGITS
    rists
    0.21
    å§Ķå±Ī
    0.19
    éĤ£ä¸Ģ天
    0.19
     Dexter
    0.18
    .paths
    0.18
    erdem
    0.18
    rå
    0.17
    å¹²éĥ¨éĺŁä¼į
    0.17
    Resistance
    0.17
    riday
    0.17
    Activations Density 0.002%

    No Known Activations