© 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. 11049
    Prev
    Next
    INDEX
    Explanations

    preposition phrase start

    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
    å¾Ģä¸Ĭ
    -0.20
    éģ¥æݧ
    -0.19
     Earl
    -0.19
    顺çĿĢ
    -0.19
    heten
    -0.18
    assist
    -0.18
     tiá»ĩn
    -0.18
    éĨĴ缮
    -0.18
    adata
    -0.18
    家ä½ı
    -0.18
    POSITIVE LOGITS
    æŶä¸į
    0.21
     sweat
    0.19
    swith
    0.19
     with
    0.19
    íĥķ
    0.19
    æ¹¾
    0.18
    neys
    0.18
    ird
    0.18
    zilla
    0.17
    ished
    0.17
    Activations Density 0.108%

    No Known Activations