© 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. 16491
    Prev
    Next
    INDEX
    Explanations

    MacGyver, Richard, Tacuba, Rauschenberg, ClanLib

    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
    çī¢åĽº
    -0.25
    éĺ´
    -0.20
    éĽĮ
    -0.20
    çĥŃéŨ
    -0.20
    æĬĵ
    -0.19
    .ast
    -0.19
    .android
    -0.18
    _hdl
    -0.18
    ErrorHandler
    -0.18
     redux
    -0.18
    POSITIVE LOGITS
    æ°ijæĹıæĸĩåĮĸ
    0.22
    æ°´èµĦæºIJ
    0.22
    身å¿ĥåģ¥åº·
    0.20
    ç²¾åĬĽ
    0.19
    æĸĩåĮĸèīºæľ¯
    0.19
    çŁ¢
    0.19
    åĪĽæĦı
    0.19
     Culture
    0.18
     sáng
    0.18
    æĸĩä½ĵ
    0.18
    Activations Density 0.159%

    No Known Activations