© 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. 12863
    Prev
    Next
    INDEX
    Explanations

    politicization, legalization, commercialization

    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
    管çIJĨåĬŀæ³ķ
    -0.21
    满æĦı度
    -0.20
    满æĦı
    -0.20
    è§ģè¯Ĩ
    -0.19
     ÐIJлекÑģан
    -0.19
    born
    -0.18
    满æĦıçļĦ
    -0.18
    emento
    -0.18
    æĿĥ
    -0.18
    itage
    -0.18
    POSITIVE LOGITS
    inde
    0.18
    ed
    0.18
    ä¸ĢåĪĩ
    0.18
    é¾Ľ
    0.17
    åħ¬ç«ł
    0.17
     Gregory
    0.17
     everything
    0.17
     struggle
    0.16
     masse
    0.16
    uck
    0.16
    Activations Density 0.016%

    No Known Activations