© 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. 11556
    Prev
    Next
    INDEX
    Explanations

    time durations

    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¿Ļæł·ä¸ĢæĿ¥
    -0.20
    arl
    -0.20
    ket
    -0.19
    è¿Ļä¸Ģ天
    -0.19
    åIJijå¾Ģ
    -0.19
    追éļı
    -0.18
    å¸ĮæľĽèĩªå·±
    -0.18
    太快
    -0.18
    ohl
    -0.18
    izr
    -0.18
    POSITIVE LOGITS
    æĪIJåĬŁ
    0.25
    èī¯å¥½
    0.24
    æĪIJåĬŁçļĦ
    0.24
    å®īçĦ¶
    0.23
     successful
    0.23
    æŃ£å¸¸ä½¿çĶ¨
    0.22
    perfect
    0.21
    successfully
    0.20
     perfect
    0.20
     successfully
    0.20
    Activations Density 0.108%

    No Known Activations