© 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. 11275
    Prev
    Next
    INDEX
    Explanations

    price discounts and savings

    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
    IJľ
    -0.20
    æĻ®æŁ¥
    -0.19
     Rou
    -0.19
    ERM
    -0.19
    å¤Ķ
    -0.17
    è¯ī讼
    -0.17
    ARN
    -0.17
    erm
    -0.17
     renown
    -0.17
    åī¯æľ¬
    -0.17
    POSITIVE LOGITS
    æİī
    0.25
    éĻįä»·
    0.24
    ä¸ĭè°ĥ
    0.24
    å¼
    0.23
    discount
    0.22
    éĿŀ常æĺİæĺ¾
    0.20
    æ®Ħ
    0.20
    æİīäºĨ
    0.20
    ä¼ĺæĥł
    0.20
    磶
    0.20
    Activations Density 0.012%

    No Known Activations