© 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. 11057
    Prev
    Next
    INDEX
    Explanations

    nitrogen and related compounds

    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
    arella
    -0.21
    ->__
    -0.21
     APPLE
    -0.20
    樾
    -0.20
    ä¸ī代
    -0.20
     cáºŃn
    -0.20
    APPLE
    -0.20
    éĶĥ
    -0.19
    èľ¡
    -0.19
    车åŀĭ
    -0.19
    POSITIVE LOGITS
    æ°®
    0.34
     nitrogen
    0.32
    Nit
    0.27
     Nit
    0.26
    nit
    0.24
     nit
    0.23
    ç¡Ŀ
    0.22
    æ°¨
    0.21
     ammonia
    0.21
    åĮĸèĤ¥
    0.20
    Activations Density 0.593%

    No Known Activations