© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12509
    Prev
    Next
    INDEX
    Explanations

    parts of Greek letters

    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
    æĸ¼
    -0.26
    æĸ¼æĺ¯
    -0.25
    èĩ³æĸ¼
    -0.25
    ä¸ĢçĤ¹åĦ¿
    -0.24
    çĤ¹åĦ¿
    -0.23
    è¿ĻåĦ¿
    -0.23
    äºĭåĦ¿
    -0.21
    úb
    -0.19
    åĵªåĦ¿
    -0.18
     fı
    -0.18
    POSITIVE LOGITS
    Ëī
    0.22
    acute
    0.21
    âĢ¾
    0.19
    ÃĮ
    0.18
    ÂĢÂĻ
    0.18
    Ùĭ
    0.18
     Pais
    0.17
     اÙĦاخ
    0.17
     Pokemon
    0.17
    åĴĮå®ĮåĸĦ
    0.17
    Activations Density 0.410%

    No Known Activations