© 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. 15790
    Prev
    Next
    INDEX
    Explanations

    revenue generation, funds, proceeds

    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
    udd
    -0.20
    dom
    -0.20
    è¡¡éĩı
    -0.19
     dom
    -0.19
    sad
    -0.19
    天é¹ħ
    -0.18
    CES
    -0.18
    endor
    -0.18
    ardo
    -0.18
    Delivery
    -0.18
    POSITIVE LOGITS
     revenue
    0.32
    æĶ¶åħ¥
    0.30
     revenues
    0.30
     proceeds
    0.27
     income
    0.27
     Generated
    0.26
     GENERATED
    0.26
     generate
    0.25
    generate
    0.25
     funds
    0.25
    Activations Density 0.123%

    No Known Activations