© 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. 14426
    Prev
    Next
    INDEX
    Explanations

    list items ending in punctuation

    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
    çĶļèĩ³
    -0.23
    çĶļèĩ³æĺ¯
    -0.20
    ä»Ģä¹ĪæŶåĢĻ
    -0.20
    åģľä¸ĭæĿ¥
    -0.19
     ROUT
    -0.19
    çļĦæĢ§æł¼
    -0.19
    å·®
    -0.18
    ä¹ĥèĩ³
    -0.18
    çĶļèĩ³è¿ĺ
    -0.18
    çİĭèĢħ
    -0.18
    POSITIVE LOGITS
    èĬ¦
    0.25
    åħ±åIJĮ
    0.24
    åIJįåįķ
    0.21
    ç»ĦæĪIJçļĦ
    0.21
    ä¸ī人
    0.21
    æĮģèĤ¡
    0.21
    åIJįä¹ī
    0.21
    åĪ°ä½į
    0.20
    è´Łè´£
    0.20
    .names
    0.19
    Activations Density 0.096%

    No Known Activations