© 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. 11511
    Prev
    Next
    INDEX
    Explanations

    primer, ribosomes, carders, needles

    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
    æĸ¹ä½į
    -0.23
    alse
    -0.21
    adir
    -0.19
    /maps
    -0.19
    หาย
    -0.18
    anker
    -0.18
    禽
    -0.18
    äººæł¼
    -0.18
    æ°´æºIJ
    -0.18
    åķĸ
    -0.18
    POSITIVE LOGITS
    è¿ĻæĶ¯
    0.22
    åIJĪéĢĤçļĦ
    0.21
    ãĤµãĤ¤ãĤº
    0.21
    éĢĤ
    0.20
     sizes
    0.20
    åŀĭåı·
    0.20
    \Console
    0.20
    åĻ¨
    0.19
    æİ¥æīĭ
    0.19
    åIJĪéĢĤ
    0.19
    Activations Density 0.006%

    No Known Activations