© 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. 14277
    Prev
    Next
    INDEX
    Explanations

    caching and cache mechanisms

    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
    .Att
    -0.25
    alach
    -0.23
    /rfc
    -0.21
    SplitOptions
    -0.21
    .jackson
    -0.19
    çļĦåľŁåľ°
    -0.19
    ITER
    -0.19
    atak
    -0.19
     restraining
    -0.19
    继ç»Ńä¿ĿæĮģ
    -0.19
    POSITIVE LOGITS
    ç¼ĵ
    0.33
     cache
    0.32
    cache
    0.30
     CACHE
    0.29
     caching
    0.29
     cached
    0.28
    æĺĤè´µ
    0.27
    Cache
    0.27
    .Cache
    0.26
    .cache
    0.25
    Activations Density 0.225%

    No Known Activations