© 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. 15355
    Prev
    Next
    INDEX
    Explanations

    Q: followed by colon

    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
    åľ°éģĵ
    -0.21
    å¾ģä¿¡
    -0.20
    intptr
    -0.19
    æľºåħ³
    -0.19
    otti
    -0.19
    IntArray
    -0.19
    çĶ·å¥³
    -0.18
     Moor
    -0.18
     overturned
    -0.18
    ç½²
    -0.18
    POSITIVE LOGITS
    éľĩèį¡
    0.31
    èµ°åĬ¿
    0.31
    è¶ĭåĬ¿
    0.29
    è·Įå¹ħ
    0.28
    æĮ¯
    0.28
    ä»Ĭ年以æĿ¥
    0.28
    涨å¹ħ
    0.28
    å¸ĤåĢ¼
    0.27
    åĽŀèIJ½
    0.27
    æĶ¶çĽĺ
    0.26
    Activations Density 0.033%

    No Known Activations