© 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. 15322
    Prev
    Next
    INDEX
    Explanations

    Copyright notice header

    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
    éĩijçīĮ
    -0.21
    bih
    -0.19
    éĹ®é¢ĺæĺ¯
    -0.19
    ä¹ı
    -0.19
    åĹľ
    -0.19
     glEnable
    -0.18
    æŶæĬ¥
    -0.18
    èı²å°Ķ
    -0.18
    âľī
    -0.18
    åŃĹåı·
    -0.17
    POSITIVE LOGITS
    icts
    0.19
    letcher
    0.19
     Soros
    0.18
     dumpster
    0.18
    ACLE
    0.18
    ä¸ķ
    0.18
     geometry
    0.17
    ä¼ĹæīĢ
    0.17
    agrid
    0.17
     Peanut
    0.17
    Activations Density 0.001%

    No Known Activations