© 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. 11203
    Prev
    Next
    INDEX
    Explanations

    company as

    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¿ŀ
    -0.23
     IM
    -0.21
    æĿ¥çļĦ
    -0.21
     Ten
    -0.20
     tally
    -0.19
    éĹŃ
    -0.19
    ä»Ģä¹Īåij¢
    -0.19
     ten
    -0.19
     lessons
    -0.19
    æµĬ
    -0.19
    POSITIVE LOGITS
    æĪĸåħ¶ä»ĸ
    0.23
    æĹłæĦı
    0.22
    ä¸įåĪ©
    0.22
    åĺīå¹´
    0.21
    æľ¬åħ¬åı¸
    0.21
    å®ŀè´¨æĢ§
    0.20
    å¦Ĥæŀľçݩ家
    0.20
    æĭĽåķĨå¼ķ
    0.20
    缺ä¹ı
    0.20
    缸åħ³æĶ¿çŃĸ
    0.19
    Activations Density 0.018%

    No Known Activations