© 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. 17255
    Prev
    Next
    INDEX
    Explanations

    archaic 'thou' and 'may', negations

    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
    åŁºæľ¬ä¸Ĭ
    -0.21
    好象
    -0.21
    ç¾¼
    -0.20
    åĢĴéľī
    -0.20
    æĢİä¹Īæł·
    -0.20
    è¿Ľå±ķæĥħåĨµ
    -0.19
    å¾Īæĥ³
    -0.19
    ãĤĵãģ§ãģĻ
    -0.19
    è¿ĩå¾Ĺ
    -0.19
    adopt
    -0.19
    POSITIVE LOGITS
    è¿ĻèĪ¬
    0.25
    ä¹ĭ人
    0.24
    åĶ¯æľī
    0.23
    ä¹ĭåĬĽ
    0.22
    åIJį为
    0.20
    ä¹ĭåľ°
    0.20
     tale
    0.20
     shall
    0.20
    ÅŁe
    0.20
    haps
    0.20
    Activations Density 0.757%

    No Known Activations