© 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. 15798
    Prev
    Next
    INDEX
    Explanations

    for the

    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
    è°¢
    -0.21
    åİ¿éķ¿
    -0.19
    STANCE
    -0.19
    ä¸įæŃ»
    -0.19
    è¿Ļéĥ¨
    -0.18
    porte
    -0.18
    é¹
    -0.18
    iger
    -0.18
    æī¬
    -0.18
    çľ·
    -0.18
    POSITIVE LOGITS
    åºĶæľīçļĦ
    0.24
     proper
    0.23
     nor
    0.21
    以人为
    0.21
    æŃ£å¸¸çļĦ
    0.21
     Ñģобой
    0.20
    ä»»ä½ķå½¢å¼ı
    0.20
    nil
    0.19
    ä¸Ģ个好çļĦ
    0.19
    èī¯å¥½çļĦ
    0.18
    Activations Density 0.011%

    No Known Activations