© 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. 10935
    Prev
    Next
    INDEX
    Explanations

    traffic regulations

    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
     Silk
    -0.22
     cush
    -0.20
    缩水
    -0.20
     shel
    -0.19
    è±¹
    -0.19
     gloss
    -0.19
    被éªĹ
    -0.19
    åºķæ°Ķ
    -0.18
    ç°ĩ
    -0.18
     dial
    -0.18
    POSITIVE LOGITS
    ç¦ģæŃ¢
    0.35
    严ç¦ģ
    0.30
    ä¸Ģå¾ĭ
    0.30
    管çIJĨæĿ¡ä¾ĭ
    0.28
    ä¸įåħģ许
    0.28
    åĮºåĨħ
    0.28
    è§Ħå®ļ
    0.27
    çļĦè§Ħå®ļ
    0.27
    ç¦ģ
    0.27
    ä¸įåĩĨ
    0.27
    Activations Density 0.018%

    No Known Activations