© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 16897
    Prev
    Next
    INDEX
    Explanations

    past tense actions and states

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸Ńåħ³
    -0.19
    èį¯ä¸ļ
    -0.19
    çħ§æł·
    -0.18
    ãĤ¿ãĥ«
    -0.18
    示æĦı
    -0.17
    请èģĶç³»
    -0.17
    æĥħåĨµè¿Ľè¡Į
    -0.17
    ä¼Ĭæĭī
    -0.17
    opause
    -0.16
    ãĤ½ãĥ¼
    -0.16
    POSITIVE LOGITS
    repid
    0.18
    _TYP
    0.18
     obed
    0.17
    ä¸ĢçĶŁ
    0.17
    ä¸įçŁ¥éģĵ
    0.17
    æĦŁè§īåĪ°
    0.17
    ($('.
    0.16
    å¾Īæ¸ħæ¥ļ
    0.16
    å°±åĥıæĺ¯
    0.16
     Orchard
    0.16
    Activations Density 0.073%

    No Known Activations