© 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. 12724
    Prev
    Next
    INDEX
    Explanations

    economic reports and organizations

    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
    color
    -0.21
    éģµå®Ī
    -0.21
    ç§ĥ
    -0.20
    ikal
    -0.20
    æŀ¹
    -0.20
    Color
    -0.20
    Awesome
    -0.19
    åĴ±ä»¬
    -0.19
    lew
    -0.19
    abee
    -0.19
    POSITIVE LOGITS
    arios
    0.21
    æĶ¿çŃĸæݪæĸ½
    0.21
    æݨåĬ¨
    0.21
    çħ§æĸĻ
    0.20
     OECD
    0.20
    çĪµå£«
    0.20
    åģ¥åº·çļĦ
    0.19
    chers
    0.19
    cheon
    0.19
    æ§Ľ
    0.19
    Activations Density 0.028%

    No Known Activations