© 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. 11612
    Prev
    Next
    INDEX
    Explanations

    century Scandinavian

    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
    翻身
    -0.19
    æ³ĵ
    -0.19
    å¯Įæ°ij
    -0.19
    /doc
    -0.18
    åı¦
    -0.18
    Eth
    -0.18
    ê
    -0.18
     champagne
    -0.17
    Century
    -0.17
    pel
    -0.17
    POSITIVE LOGITS
    椰
    0.21
     grav
    0.19
     grip
    0.19
    åĶ¬
    0.18
    enic
    0.18
    à¸Ĥà¸Ļา
    0.18
    æĪIJè´¥
    0.18
    alia
    0.18
    adio
    0.18
    -photo
    0.18
    Activations Density 0.012%

    No Known Activations