© 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. 13002
    Prev
    Next
    INDEX
    Explanations

    advertising or selling

    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
    utely
    -0.20
    å£ħ
    -0.20
    æµĩ
    -0.20
    èĦ¾
    -0.20
    _wave
    -0.19
    åľ¨åĽ½å¤ĸ
    -0.19
    èļģ
    -0.19
     geçmiÅŁ
    -0.19
    éļħ
    -0.19
    å°ķ
    -0.18
    POSITIVE LOGITS
    广åijĬ
    0.26
     Advertising
    0.25
     advertising
    0.24
    Advertising
    0.23
     advertis
    0.22
     advertise
    0.21
    å¼Ģåıij
    0.20
     advertisement
    0.20
    æĽ´å¤§çļĦ
    0.19
    çķĻè¨ĢæĿ¿
    0.19
    Activations Density 0.005%

    No Known Activations