© 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. 13479
    Prev
    Next
    INDEX
    Explanations

    May blessings

    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
    大éĩıçļĦ
    -0.23
    äºĮ线
    -0.21
    大éĩı
    -0.21
    ibal
    -0.19
     Parad
    -0.19
    æ¸ħæ¥ļ
    -0.19
    beh
    -0.18
    忽è§Ĩ
    -0.18
    认è¯ĨåĪ°
    -0.18
    å·®è·Ŀ
    -0.18
    POSITIVE LOGITS
    ç¥ĿæĦ¿
    0.32
    好è¿IJ
    0.31
    ç»ĵå±Ģ
    0.30
    顺åĪ©
    0.28
    åij½è¿IJ
    0.27
     outcomes
    0.26
    è¿IJåĬ¿
    0.26
    è¿IJæ°Ķ
    0.25
    æĪIJåĬŁçİĩ
    0.25
    ç¥Ī祷
    0.24
    Activations Density 0.098%

    No Known Activations