© 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. 12368
    Prev
    Next
    INDEX
    Explanations

    never thought

    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
     اÙĦÙĨÙĤ
    -0.24
    loi
    -0.19
    åĭ¿
    -0.19
    колÑĮ
    -0.19
    ä¸į妨
    -0.18
    宽æĿ¾
    -0.18
    ä½łä¼ļåıijçİ°
    -0.18
    SPI
    -0.18
    æ¦Ķ
    -0.18
    åį´æ²¡æľī
    -0.18
    POSITIVE LOGITS
    è¿Ļä¹Īå¤ļ
    0.29
    è¿Ļä¹Ī
    0.28
    å¦ĤæѤ
    0.27
     anything
    0.26
    æľīä»»ä½ķ
    0.26
    éĤ£ä¹Īç®Ģåįķ
    0.24
    anything
    0.24
    éĢĻ麼
    0.24
    è¿Ļæł·çļĦè¯Ŀ
    0.23
    è¿Ļä¹Īä¹ħ
    0.22
    Activations Density 0.039%

    No Known Activations