© 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. 11187
    Prev
    Next
    INDEX
    Explanations

    foreign words and names

    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
    累累
    -0.19
    á»IJ
    -0.18
    çĪ¨
    -0.18
    lac
    -0.18
    大éĩı
    -0.18
    OUCH
    -0.17
    itur
    -0.17
    heid
    -0.17
    åħ¥
    -0.16
    itics
    -0.16
    POSITIVE LOGITS
    å¿łå®ŀ
    0.20
    ä¹ĭ家
    0.19
    è¹ī
    0.19
    èģļ
    0.19
    errs
    0.19
    éĤ£è¾¹
    0.18
    Crypt
    0.18
    thead
    0.18
    åĢ¬
    0.18
    .Err
    0.18
    Activations Density 0.127%

    No Known Activations