© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12367
    Prev
    Next
    INDEX
    Explanations

    contagious, infectious, catchy, addictive

    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
    ç¢Į
    -0.18
    æµģæĺŁ
    -0.18
    åĽ½åĨħå¸Ĥåľº
    -0.17
    åĽ½æĥħ
    -0.16
    cts
    -0.16
    踬
    -0.16
    æĿı
    -0.16
    bez
    -0.16
    posta
    -0.16
    å±ķå¼Ģ
    -0.15
    POSITIVE LOGITS
    æĢ§å¼º
    0.32
    iveness
    0.24
    empo
    0.23
    æĢ§åĴĮ
    0.23
    æĢ§çļĦ
    0.22
    ively
    0.22
     incumbent
    0.21
    ness
    0.20
    èIJľ
    0.20
    æĢ§çĸ¾çĹħ
    0.20
    Activations Density 0.008%

    No Known Activations