© 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. 16901
    Prev
    Next
    INDEX
    Explanations

    diazepam binding inhibitor

    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
    è¾ľ
    -0.20
     bè
    -0.18
    æ¥
    -0.18
    OrUpdate
    -0.17
    ÑĮÑı
    -0.17
    éĿ¢åŃIJ
    -0.16
    åĢ¼å¾Ĺä¸ĢæıIJ
    -0.16
    ÑĢÑĥг
    -0.16
    æĢ§åij½
    -0.15
     ÑģлÑĥÑĩаÑı
    -0.15
    POSITIVE LOGITS
    olin
    0.18
    æľ¦èĥ§
    0.17
    Ñħи
    0.17
    ockey
    0.16
    enz
    0.16
    NCY
    0.16
    inne
    0.16
    olic
    0.15
    ä¹IJåĽ¢
    0.15
    suit
    0.15
    Activations Density 0.013%

    No Known Activations