© 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. 13518
    Prev
    Next
    INDEX
    Explanations

    artist albums

    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
    æľīæīĢ
    -0.23
    屯
    -0.22
    ä¸İåIJ¦
    -0.20
    eled
    -0.19
    azy
    -0.19
    åŁº
    -0.19
    éĦĻ
    -0.19
    edis
    -0.18
     patent
    -0.18
    bst
    -0.18
    POSITIVE LOGITS
    æ¸ĹéĢı
    0.25
    çĸµ
    0.23
    Ø£ÙĦ
    0.22
    é£İåIJ¹
    0.19
    æµģåIJij
    0.19
    алÑĮ
    0.19
     Interr
    0.19
     Dollars
    0.18
    è¯¾æľ¬
    0.18
     Seam
    0.18
    Activations Density 0.043%

    No Known Activations