© 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. 15048
    Prev
    Next
    INDEX
    Explanations

    than what

    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
    ัà¸ģษ
    -0.21
    å¤ļä½ĻçļĦ
    -0.20
    éģķãģ£ãģ¦
    -0.19
    èĢĮè¿Ļ
    -0.19
    å´¦
    -0.19
    æĪij没
    -0.18
     tentang
    -0.17
    angep
    -0.17
    è¿Ļ段
    -0.17
     unpopular
    -0.17
    POSITIVE LOGITS
    å¯Ħæīĺ
    0.23
    åľ¨è·¯ä¸Ĭ
    0.21
    åľ¨äº¬
    0.21
    åľ¨å¤ĸ
    0.20
    ä½ĵçİ°åľ¨
    0.20
    åľ¨æł¡
    0.20
    å¯Ħ
    0.20
    æĤ¬æĮĤ
    0.20
    åľ¨çĶŁæ´»ä¸Ń
    0.20
    åľ¨å¸Ĥåľºä¸Ĭ
    0.19
    Activations Density 0.034%

    No Known Activations