© 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. 16686
    Prev
    Next
    INDEX
    Explanations

    cost reduction and technological improvement

    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
     заÑĢегиÑģÑĤ
    -0.21
    ugins
    -0.20
    icont
    -0.19
    lick
    -0.19
    \Model
    -0.19
    身ä½ĵåģ¥åº·
    -0.19
    .assertj
    -0.19
    äºĪ
    -0.18
    æıŃéľ²
    -0.18
    <src
    -0.18
    POSITIVE LOGITS
     technology
    0.32
    æĪIJæľ¬
    0.31
    technology
    0.30
     cost
    0.29
    ãĤ³ãĤ¹ãĥĪ
    0.25
    çļĦæĪIJæľ¬
    0.25
     costs
    0.24
    æĬĢæľ¯
    0.24
     prohib
    0.24
     technologies
    0.24
    Activations Density 0.311%

    No Known Activations