© 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. 15548
    Prev
    Next
    INDEX
    Explanations

    already

    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
    å§ĭç»Ī
    -0.27
    å§ĭç»Īä¿ĿæĮģ
    -0.26
    çªģçĦ¶
    -0.24
    ä»İæѤ
    -0.23
    æľĢç»Ī
    -0.23
     ÑĤакже
    -0.22
    æŃ£å¥½
    -0.22
    ç»Īäºİ
    -0.21
    å§ĭç»ĪåĿļæĮģ
    -0.21
    åIJĮæĹ¶ä¹Ł
    -0.20
    POSITIVE LOGITS
     already
    0.42
    å·²ç»ıåľ¨
    0.41
    Already
    0.41
    already
    0.40
    就已ç»ı
    0.36
     Already
    0.36
    å·²ç»ıæľī
    0.35
    å·²ç»ıæĺ¯
    0.35
    å·²åľ¨
    0.33
    æĪijå·²ç»ı
    0.32
    Activations Density 0.091%

    No Known Activations