© 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. 11354
    Prev
    Next
    INDEX
    Explanations

    interventions in Africa

    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
    .isOn
    -0.20
    å¾Ĺ天
    -0.20
    æĶ¶
    -0.20
    å´Ľ
    -0.19
    æĹłäºº
    -0.19
    åħļåĴĮ
    -0.19
    éķ¿å¾Ĺ
    -0.18
     Gast
    -0.18
    没人
    -0.18
    æĥ³åĥı
    -0.17
    POSITIVE LOGITS
    åIJİèĢħ
    0.21
    ¢åįķ
    0.19
    mlink
    0.18
    åı¦ä¸Ģæĸ¹éĿ¢
    0.17
    æѤå¤ĸ
    0.17
    pls
    0.17
    uber
    0.17
    orent
    0.17
    (;
    0.17
    ubre
    0.17
    Activations Density 1.088%

    No Known Activations