© 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. 16601
    Prev
    Next
    INDEX
    Explanations

    spread or distributed

    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
    ä¸ĢèĦļ
    -0.19
    othermal
    -0.18
    ÅĪ
    -0.18
    ell
    -0.18
    graphs
    -0.17
    SES
    -0.17
    亿åIJ¨
    -0.17
    æĮł
    -0.17
    èķ¨
    -0.17
    ouro
    -0.17
    POSITIVE LOGITS
    å¼ĢæĿ¥
    0.40
     khắp
    0.32
    åĩºåİ»
    0.31
     spread
    0.31
    èĶĵ延
    0.30
    åĪĨå¸ĥ
    0.29
    éģįåıĬ
    0.28
    æķ£å¸ĥ
    0.28
    åĪĨå¸ĥåľ¨
    0.27
     across
    0.27
    Activations Density 0.148%

    No Known Activations