© 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. 10910
    Prev
    Next
    INDEX
    Explanations

    food and scientific terms

    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
    floating
    -0.20
    ç¢ĺ
    -0.20
    é£İåIJ¹
    -0.19
    åĵ¥ä¼¦
    -0.19
    odo
    -0.19
    裸
    -0.19
    edly
    -0.19
    (surface
    -0.18
    çĿ¬
    -0.18
    èĬĤæĹ¥
    -0.18
    POSITIVE LOGITS
    æĪIJåĬŁ
    0.22
    æ¯ĵ
    0.21
     Glover
    0.20
    езÑĥлÑĮÑĤаÑĤ
    0.19
    mars
    0.19
    Successful
    0.19
    æŃ¥
    0.19
     Hamas
    0.19
     Batter
    0.18
    ãģĨãģ¾ãģı
    0.18
    Activations Density 0.020%

    No Known Activations