© 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. 11277
    Prev
    Next
    INDEX
    Explanations

    local businesses and owners

    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
    é¹ij
    -0.22
    ç§ijæĬĢèĤ¡ä»½
    -0.21
    åħ¨åijĺ
    -0.20
    æīĵçĮİ
    -0.19
    raph
    -0.19
    窣
    -0.19
    çľģæķĻèĤ²åİħ
    -0.19
    вали
    -0.19
    неÑĤ
    -0.19
    çľģéĴ±
    -0.19
    POSITIVE LOGITS
     local
    0.25
    è¡Ĺ
    0.25
     vic
    0.24
    åħ¬å¹³
    0.23
    local
    0.23
    éŨåı£
    0.23
    ç»ıèIJ¥èĢħ
    0.23
     businesses
    0.23
    (local
    0.22
    Local
    0.22
    Activations Density 0.025%

    No Known Activations