© 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. 16190
    Prev
    Next
    INDEX
    Explanations

    real estate sales and transactions

    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
     appropriate
    -0.21
    è¦Ĩ
    -0.20
    abet
    -0.19
    enty
    -0.19
     appropriately
    -0.19
    æĵ¿
    -0.19
    .observe
    -0.19
    æĴŃ
    -0.19
     Purch
    -0.18
    æ¯ı天éĥ½
    -0.18
    POSITIVE LOGITS
    éĹ²ç½®
    0.20
    _remain
    0.19
    å®ļä»·
    0.19
    æĶ¹éĢł
    0.19
    ç¥ĸ
    0.18
    çĽĺæ´»
    0.18
    èĩªå®¶
    0.18
    æļĤç¼ĵ
    0.18
     hire
    0.18
    èĩªå·±çļĦ
    0.18
    Activations Density 0.013%

    No Known Activations