© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12352
    Prev
    Next
    INDEX
    Explanations

    interest rates

    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
    åĩĨ
    -0.23
    æĮĩå°ĸ
    -0.22
    åĩĨåħ¥
    -0.21
    åĹħ
    -0.20
    uptime
    -0.19
    routine
    -0.19
    atedRoute
    -0.18
    ç«ĻçĿĢ
    -0.18
    ups
    -0.18
    GLE
    -0.18
    POSITIVE LOGITS
    çİĩ
    0.31
     rate
    0.30
     rates
    0.29
     Rate
    0.29
    Rates
    0.28
    Rate
    0.28
    çİĩ为
    0.28
    rate
    0.28
    -rate
    0.28
     Rates
    0.28
    Activations Density 0.013%

    No Known Activations