© 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. 11298
    Prev
    Next
    INDEX
    Explanations

    national issues and contexts

    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
     Humanities
    -0.21
    çĹħæ¯ĴæĦŁæŁĵ
    -0.20
    ãĤĬ
    -0.18
    人éĢī
    -0.18
    reopen
    -0.17
    zelf
    -0.17
     Visualization
    -0.17
    ãģĦ
    -0.17
    å·¥ä½ľç«Ļ
    -0.17
    gid
    -0.17
    POSITIVE LOGITS
    ities
    0.34
    åĴĮåľ°åĮº
    0.26
    ized
    0.26
    idad
    0.24
    éĹ´çļĦ
    0.23
    izing
    0.22
    åĮĸçļĦ
    0.22
    ization
    0.21
    iteit
    0.21
    çĶŁäº§æĢ»åĢ¼
    0.21
    Activations Density 0.017%

    No Known Activations