© 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
    2. Qwen3-14B
    3. 20-RESID-BATCHTOPK-65K__L0-80
    4. 13975
    Prev
    Next
    INDEX
    Explanations

    Chinese conjunctions and outcomes

    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
    استÙģ
    -0.23
    اÙĦتز
    -0.22
    ÙħصاÙĦ
    -0.22
    ä¿Ŀ驾æĬ¤
    -0.22
    á´¼
    -0.22
    ä½łèĩªå·±
    -0.22
    Õ§
    -0.22
    سÙĤÙĪ
    -0.22
    ÙħصÙĦ
    -0.21
    ÙħصÙĦØŃØ©
    -0.21
    POSITIVE LOGITS
    使å¾Ĺ
    0.31
    ä½Ĩçͱäºİ
    0.31
    å¹¶å°Ĩ
    0.30
    ä¸Ķ
    0.30
    å¹¶ä¸Ķ
    0.29
    ä½Ĩ
    0.26
    å¹¶éĢļè¿ĩ
    0.26
    ç¡®ä¿Ŀ
    0.25
    å¹¶åľ¨
    0.25
    åĽłæŃ¤
    0.25
    Activations Density 0.404%

    No Known Activations