© 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. 12602
    Prev
    Next
    INDEX
    Explanations

    a win

    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
    è±¢
    -0.22
    åħ¶å®ĥéĹ®é¢ĺ
    -0.21
    åĽŁ
    -0.21
    å±ĬæŶ
    -0.20
    åĪ«çļĦ
    -0.20
    ä¸ĢæĶ¯
    -0.19
    è¿Ļåıª
    -0.19
     undermin
    -0.19
    è¿Ļä¸ªåľ°æĸ¹
    -0.19
    IRST
    -0.19
    POSITIVE LOGITS
    çĿĢ
    0.24
    rzy
    0.21
    æĮģ
    0.20
    黾
    0.20
    ly
    0.19
    äºĶå¹´
    0.19
    oti
    0.19
    两年
    0.19
    åľ¨å¹¿å·ŀ
    0.19
     snapped
    0.18
    Activations Density 0.043%

    No Known Activations