© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15147
    Prev
    Next
    INDEX
    Explanations

    medical surface

    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
    å½Ĵå±ŀäºİ
    -0.24
    orda
    -0.20
    ninger
    -0.19
    æ²IJæµ´
    -0.19
    олов
    -0.18
    &amp
    -0.18
    Sizer
    -0.18
    åĽ½ç±į
    -0.18
    æĪ·ç±į
    -0.17
    oko
    -0.17
    POSITIVE LOGITS
    ãģij
    0.21
     Randall
    0.20
    adder
    0.19
    åı¨
    0.19
    ãĥ¼ãĤ¹
    0.19
    æħĪæĤ²
    0.17
    bio
    0.17
     обла
    0.17
    ÑīиÑĤ
    0.17
    æ´ŀå¯Ł
    0.16
    Activations Density 0.830%

    No Known Activations