© 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. 10802
    Prev
    Next
    INDEX
    Explanations

    revenue and income generation

    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
    Observer
    -0.21
    æĦŁè§¦
    -0.21
    observer
    -0.21
    ä¼łè¯´
    -0.19
     Trades
    -0.19
    itte
    -0.19
    æĦŁæĤŁ
    -0.19
    æĦŁåºĶ
    -0.18
     возд
    -0.18
    npos
    -0.18
    POSITIVE LOGITS
    æĿ¥æºIJ
    0.25
    .infinity
    0.21
    _OM
    0.21
    ¢åįķ
    0.20
    æºIJæ³ī
    0.19
     hạng
    0.19
    å¤ļåħĥåĮĸ
    0.19
     Kensington
    0.18
    haul
    0.18
    æ¦ľ
    0.18
    Activations Density 0.040%

    No Known Activations