© 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. 12950
    Prev
    Next
    INDEX
    Explanations

    amusement rides

    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
     lá»Ļ
    -0.23
    uels
    -0.20
    ãĤ³ãĥ¼ãĥĴãĥ¼
    -0.19
    åĽ½æĥħ
    -0.19
    æŀķ头
    -0.19
    å±ħ室
    -0.19
    èįŀ
    -0.19
    榧
    -0.19
    èĮ¬
    -0.19
    .Dom
    -0.19
    POSITIVE LOGITS
    游ä¹IJ
    0.29
     amusement
    0.25
    åĦ¿ç«¥
    0.22
    åİ
    0.22
     Disneyland
    0.22
    çİ©åħ·
    0.21
    .Resolve
    0.21
     ven
    0.21
     carnival
    0.21
     rides
    0.20
    Activations Density 0.015%

    No Known Activations