© 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. 11484
    Prev
    Next
    INDEX
    Explanations

    price, discount, offer, registration, sale

    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
     chain
    -0.23
    Chain
    -0.20
    age
    -0.20
    ä¸Ĭå®ĺ
    -0.20
    bal
    -0.20
    chain
    -0.19
    @@
    -0.19
    HOUSE
    -0.19
    (chain
    -0.19
    éĹ¼
    -0.18
    POSITIVE LOGITS
    éĢĢ
    0.23
    票价
    0.21
    ç»ĦåĽ¢
    0.21
    orta
    0.20
    æĶ¶æķĽ
    0.20
    éĺ¶æ®µ
    0.20
    ElementType
    0.20
    èį§
    0.20
    åĬŁæķĪ
    0.19
    æĪªæŃ¢
    0.19
    Activations Density 0.003%

    No Known Activations