© 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. 11706
    Prev
    Next
    INDEX
    Explanations

    isn't, aren't, don't

    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
    趣
    -0.23
    æµģæĺŁ
    -0.19
    说åĩºæĿ¥
    -0.19
    山寨
    -0.19
    å½ĵåľ°äºº
    -0.19
     [&](
    -0.18
    rey
    -0.18
    ↵↵
    -0.18
    çļĦ帮åĬ©ä¸ĭ
    -0.18
    éĿłè°±
    -0.18
    POSITIVE LOGITS
    æĺİæĺİ
    0.35
     przecież
    0.24
    åĽº
    0.23
    åĪĨæĺİ
    0.23
    éĤ£ä¹Īå¤ļ
    0.21
    oard
    0.21
     supposed
    0.21
    è¿ĺ以为
    0.21
    æ³±
    0.20
     ведÑĮ
    0.20
    Activations Density 0.151%

    No Known Activations