© 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. 15825
    Prev
    Next
    INDEX
    Explanations

    start of

    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
    MAN
    -0.19
    èµ°åĩºåİ»
    -0.19
     thou
    -0.18
    åĪ°è´¦
    -0.18
    åıĭ
    -0.17
    æľĭåıĭ
    -0.17
     Ñģобой
    -0.17
    uzzi
    -0.17
    .Ap
    -0.17
    çľĭçľĭ
    -0.17
    POSITIVE LOGITS
    /end
    0.23
    æĹħç¨ĭ
    0.21
     proceedings
    0.21
    漫éķ¿çļĦ
    0.20
    éĤº
    0.20
     festivities
    0.19
     Formal
    0.19
    åºıå¹ķ
    0.18
    æĸ°ä¸Ģè½®
    0.18
    迹象
    0.18
    Activations Density 0.043%

    No Known Activations