© 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. 12830
    Prev
    Next
    INDEX
    Explanations

    volume citations

    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
     ÐŁÐ¾Ñĩем
    -0.21
    åİŁæłĩé¢ĺ
    -0.21
    åĬŁ
    -0.20
    ä¸į管
    -0.20
    æĺŁçº§
    -0.20
    好æĦŁ
    -0.19
    aba
    -0.19
    åįłçĶ¨
    -0.19
    CMS
    -0.18
     Cbd
    -0.18
    POSITIVE LOGITS
    -http
    0.22
     spep
    0.20
     http
    0.20
    æħ¢æħ¢çļĦ
    0.19
     danmark
    0.19
    ï¿ł
    0.19
     odense
    0.19
    http
    0.18
     Spl
    0.18
    Ħìŀ¬
    0.18
    Activations Density 0.089%

    No Known Activations