© 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. 14181
    Prev
    Next
    INDEX
    Explanations

    scientific names after punctuation

    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
     whistle
    -0.19
    æħĮ
    -0.18
    iren
    -0.18
    inal
    -0.17
    ä¸ŃåįİæĸĩåĮĸ
    -0.17
    è¸ħ
    -0.17
    åĽ½éĻħåľ¨çº¿
    -0.16
    åĽ¤
    -0.16
    isoft
    -0.16
    оваÑĢ
    -0.16
    POSITIVE LOGITS
    æŁIJ个
    0.21
    å¤ļç§įå½¢å¼ı
    0.21
    alte
    0.20
    çī¹åĪ«æĺ¯
    0.19
    éĩĮéĿ¢çļĦ
    0.19
    çī¹æľīçļĦ
    0.18
    åĭĥ
    0.18
    åİŁæľīçļĦ
    0.18
    odem
    0.18
    erate
    0.18
    Activations Density 0.480%

    No Known Activations