© 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. 13996
    Prev
    Next
    INDEX
    Explanations

    medical referrals and departments

    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
     Fortune
    -0.21
    å¥ĸ
    -0.20
    è¤Ĵ
    -0.18
    PEAT
    -0.18
    LOCKS
    -0.18
    assel
    -0.17
    æĿ¥èĩª
    -0.17
     fortune
    -0.17
     gang
    -0.17
     Gang
    -0.17
    POSITIVE LOGITS
    æ³Ľ
    0.24
    æĹ¥å¸¸
    0.23
    æ°¾
    0.22
    æĹ¥å¸¸çĶŁæ´»
    0.22
    биÑĤ
    0.20
    æĭ¨æīĵ
    0.20
    ä¸ĬæĬ¥
    0.20
    èĥĢ
    0.20
    è°´
    0.19
    çĶŁæ´»æĸ¹å¼ı
    0.19
    Activations Density 0.014%

    No Known Activations