© 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. 13396
    Prev
    Next
    INDEX
    Explanations

    sell copies

    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
    dock
    -0.21
    ief
    -0.21
    åıĪ好åıĪå¿«
    -0.18
    æīįçŁ¥éģĵ
    -0.18
     Moderator
    -0.18
    æ§
    -0.18
    åľį
    -0.18
    纵深
    -0.17
    åĽ´
    -0.17
    æĹłè®ºæĺ¯
    -0.17
    POSITIVE LOGITS
    _PRINTF
    0.20
    RID
    0.20
    åıĺçİ°
    0.19
    æ¤Ł
    0.19
    OPY
    0.18
     outright
    0.18
    åįĸç»Ļ
    0.18
    ç»ıèIJ¥æ´»åĬ¨
    0.18
     bulk
    0.18
    åĩĮ
    0.18
    Activations Density 0.008%

    No Known Activations