© 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. 15705
    Prev
    Next
    INDEX
    Explanations

    or, punctuation, non-Latin scripts

    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
    epad
    -0.24
    å¾¼
    -0.20
    大éŨ
    -0.19
    _DEC
    -0.18
     вли
    -0.17
    ей
    -0.17
    lav
    -0.17
    onom
    -0.17
    -many
    -0.17
    ¢åįķ
    -0.17
    POSITIVE LOGITS
    ä»»ä½ķå½¢å¼ı
    0.23
    æĪĸ
    0.23
    æĪĸèĢħ
    0.23
    æĪĸåħ¶ä»ĸ
    0.22
    หร
    0.22
    æĪĸèĢħæĺ¯
    0.22
     наÑĢко
    0.22
     ëĺIJëĬĶ
    0.22
     hoặc
    0.22
    ãģĤãĤĭãģĦãģ¯
    0.22
    Activations Density 0.046%

    No Known Activations