© 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. 10801
    Prev
    Next
    INDEX
    Explanations

    political officials and titles

    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
    èĮ«èĮ«
    -0.20
    çłĶ究éĻ¢
    -0.19
    伫
    -0.19
    çªĪ
    -0.18
     outs
    -0.18
    æĻ¯å¾·
    -0.18
     ÑģÑĤÑĢаÑħов
    -0.18
    主ä¹īèĢħ
    -0.17
    æĥĨ
    -0.17
    çĬĦ
    -0.17
    POSITIVE LOGITS
    åĴĮ社ä¼ļ
    0.24
    è®®åijĺ
    0.22
    åħ¼
    0.21
    们çļĦ
    0.21
    /pol
    0.20
    ric
    0.20
    iale
    0.20
    ç®ķ
    0.19
    åĢĻéĢī人
    0.19
    级åĪ«çļĦ
    0.19
    Activations Density 0.027%

    No Known Activations