© 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. 14861
    Prev
    Next
    INDEX
    Explanations

    score

    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
    ital
    -0.20
    大éĩı
    -0.20
    大éĩıçļĦ
    -0.19
    æºĸ
    -0.19
    æľī大éĩıçļĦ
    -0.18
    sst
    -0.18
     Hubbard
    -0.17
    稷
    -0.17
    家ä½ı
    -0.17
     defect
    -0.17
    POSITIVE LOGITS
    ä¸Ńæĸ°
    0.23
    饯
    0.22
    åľ¨è¿Ļ个
    0.20
    ä¹Łéļıä¹ĭ
    0.19
    Leaks
    0.18
    uÃŃ
    0.18
     Keeps
    0.17
    _FM
    0.17
    ива
    0.17
    è´Ń票
    0.17
    Activations Density 0.024%

    No Known Activations