© 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. 15187
    Prev
    Next
    INDEX
    Explanations

    Ch, New, Sch, Double, Chino

    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
     ÅļwiÄĻt
    -0.27
     Erotische
    -0.27
     Detaylı
    -0.24
     uçu
    -0.24
     mükem
    -0.22
    schlü
    -0.22
    à¹Ģà¸Ĺà¸Ħà¹Ĥà¸Ļ
    -0.21
     обоÑĢ
    -0.21
     Müd
    -0.21
     Atatür
    -0.20
    POSITIVE LOGITS
    åIJģ
    0.20
    çłĶ究éĻ¢
    0.19
    aker
    0.19
    ä¸įå°½
    0.19
    åħ¬å¼Ģåıijè¡Į
    0.19
    æĪ¢
    0.19
    æĥķ
    0.18
     halk
    0.18
    éĻ¢åī¯éĻ¢éķ¿
    0.18
    ãĤ«ãĥĥãĥĹ
    0.18
    Activations Density 0.033%

    No Known Activations