© 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. 13942
    Prev
    Next
    INDEX
    Explanations

    debut or first appearance

    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
     confl
    -0.20
     pec
    -0.20
    稳
    -0.19
    严å¯Ĩ
    -0.19
    ä¹±
    -0.19
    åı¯ä¾Ľ
    -0.18
     qual
    -0.18
    å°ıä¼ĻåŃIJ
    -0.18
    .bat
    -0.18
    åĤį
    -0.18
    POSITIVE LOGITS
    äº®çĽ¸
    0.39
    çĻ»åľº
    0.34
    åĩºçİ°åľ¨
    0.26
    åĩºåľº
    0.22
     headlines
    0.21
     debut
    0.21
     вÑĭÑħод
    0.20
    æĿ¥åĪ°
    0.20
    isas
    0.19
    è¿Ľé©»
    0.19
    Activations Density 0.023%

    No Known Activations