© 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. 13906
    Prev
    Next
    INDEX
    Explanations

    website publications

    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
    嵩
    -0.22
    åĽ¾çº¸
    -0.21
    ìĨIJ
    -0.20
    ivos
    -0.19
    es
    -0.18
     Fame
    -0.18
     Pornhub
    -0.18
     Hogwarts
    -0.18
     tang
    -0.18
    ium
    -0.17
    POSITIVE LOGITS
    .com
    0.28
    ç½ijé¦ĸ页
    0.22
     magazine
    0.22
    è´¢ç»ı
    0.21
    æĹĹä¸ĭ
    0.21
    ç»ı纬
    0.21
    æĬ¥éģĵ
    0.20
    æĸ°éĹ»ç½ij
    0.20
    -dot
    0.19
    ä¸ĵ访
    0.19
    Activations Density 0.060%

    No Known Activations