© 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. 16278
    Prev
    Next
    INDEX
    Explanations

    booking rates and reservations

    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
    æįIJåĬ©
    -0.21
    å¨ĺ家
    -0.20
     elect
    -0.20
    åįĹè·¯
    -0.20
     дÑĥÑħ
    -0.20
    жд
    -0.19
    è£ģ
    -0.19
     dev
    -0.18
     backstage
    -0.18
    磻
    -0.18
    POSITIVE LOGITS
    åħ¥ä½ı
    0.27
    é¢Ħ订
    0.26
     booking
    0.24
     booked
    0.24
    ä½ı宿
    0.23
    æĹºåŃ£
    0.23
     bookings
    0.22
    æĪ¿ä»·
    0.22
    çŁŃæľŁ
    0.21
    ä¼ģä¸ļæıIJä¾Ľ
    0.21
    Activations Density 0.015%

    No Known Activations