© 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. 16532
    Prev
    Next
    INDEX
    Explanations

    submit, embed, enable, arrange, view, skip, change

    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
     EÄŁ
    -0.21
    åĩłå¼ł
    -0.19
     ().
    -0.19
     khá
    -0.18
    çŁ£
    -0.18
    .Disclaimer
    -0.18
    iams
    -0.17
    .mass
    -0.17
    enne
    -0.17
     zwar
    -0.17
    POSITIVE LOGITS
    ï¼ĮåĪĻ
    0.26
    çļĦè¯Ŀ
    0.26
    æĪĸèĢħåħ¶ä»ĸ
    0.22
    æľīä»»ä½ķ
    0.22
    ï¼Į请
    0.21
    请çĤ¹åĩ»
    0.21
    çļĦ話
    0.21
    æĪĸåħ¶ä»ĸ
    0.20
    èİ·å¾ĹæĽ´å¤ļ
    0.20
    ÑĢÑĥг
    0.20
    Activations Density 0.035%

    No Known Activations