© 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. 11837
    Prev
    Next
    INDEX
    Explanations

    viewsNewIn

    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
    uhan
    -0.23
    uman
    -0.21
     promises
    -0.20
     Baron
    -0.19
    ECH
    -0.19
    anka
    -0.19
    .Namespace
    -0.19
    æī¿è¯º
    -0.19
    ambi
    -0.18
    ìķ¤
    -0.18
    POSITIVE LOGITS
    äºĨ好å¤ļ
    0.25
    Spot
    0.21
    âĶ
    0.21
    бег
    0.20
    é£ı
    0.20
    人次
    0.19
    åıijæĮ¥äºĨ
    0.19
    å¯Ŀ
    0.19
    äºĨèĩªå·±çļĦ
    0.19
    ä¸ĩ人次
    0.19
    Activations Density 0.007%

    No Known Activations