© 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. 14173
    Prev
    Next
    INDEX
    Explanations

    pay bills and debts

    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
    æĹłç¼ĺ
    -0.22
    prep
    -0.20
    nap
    -0.20
    pad
    -0.19
    åĶ§
    -0.19
    arma
    -0.19
    åĪĨæķ£
    -0.19
    åĸ³
    -0.19
     ÑĦоÑĢмÑĥ
    -0.18
    è¢ĸ
    -0.18
    POSITIVE LOGITS
    åIJĦ项
    0.23
    è¿IJ转
    0.21
    itur
    0.20
    è¾¹éĻħ
    0.19
     obligations
    0.19
    ãģªãĤīãģªãģĦ
    0.19
    плаÑĤ
    0.19
    顾
    0.18
     Zi
    0.18
    inx
    0.18
    Activations Density 0.017%

    No Known Activations