© 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. 14060
    Prev
    Next
    INDEX
    Explanations

    copyright notices

    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
    lsi
    -0.21
    åľ¨ä¸Ģ
    -0.19
    ãģ¨ãģĦãģ£ãģ¦ãĤĤ
    -0.18
    amage
    -0.17
    ken
    -0.17
    veh
    -0.17
    æľ«
    -0.17
    å¹£
    -0.17
    å°±æĺ¯åĽłä¸º
    -0.17
    å§Ĺ
    -0.17
    POSITIVE LOGITS
    å¿ĻçĿĢ
    0.22
    æĹĹä¸ĭ
    0.22
    æĹĹä¸ĭçļĦ
    0.22
    ®
    0.22
    宿
    0.21
     Inc
    0.21
    殿åłĤ
    0.20
     Ltd
    0.20
    ä¹ĭä¸Ĭ
    0.19
    âĵĩ
    0.18
    Activations Density 0.086%

    No Known Activations