© 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. 11156
    Prev
    Next
    INDEX
    Explanations

    spending money or paying

    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
    simd
    -0.20
    TY
    -0.20
    秧
    -0.20
    adj
    -0.19
    èijŃ
    -0.18
    缼ä¼ļ
    -0.18
    ç¦ıåĪ©
    -0.18
    MC
    -0.18
    è¦ģç´§
    -0.18
    ni
    -0.18
    POSITIVE LOGITS
    ä¹°åĪ°
    0.33
    è´Ńä¹°
    0.31
    ä¹°çļĦ
    0.29
    ä¹°
    0.27
    ä¹°äºĨ
    0.27
    æĬķåħ¥
    0.26
    åĪ·
    0.24
    Paid
    0.23
     buying
    0.23
     buys
    0.23
    Activations Density 0.084%

    No Known Activations