© 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. 16352
    Prev
    Next
    INDEX
    Explanations

    browser functionality and compatibility

    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
    ä¸ĢåĿĹ
    -0.20
     effectively
    -0.19
    kas
    -0.19
    ä¸Ģæŀ¶
    -0.19
    çļĦçľ¼
    -0.19
    anium
    -0.19
    è¿«
    -0.18
    liable
    -0.18
    ä¸Ģè¾Ĩ
    -0.17
    åīįèĢħ
    -0.17
    POSITIVE LOGITS
     browsers
    0.21
    åħ¼å®¹
    0.21
    èī²å½©
    0.21
     view
    0.20
    æµģéĩı
    0.20
     viewed
    0.20
    æľīèī²
    0.20
    	view
    0.20
    æµıè§ĪåĻ¨
    0.20
     Compatible
    0.19
    Activations Density 0.011%

    No Known Activations