© 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. 11764
    Prev
    Next
    INDEX
    Explanations

    Palin, Meghan, Q

    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
    çļĦç«ŀäºī
    -0.20
    ÙħاÙĨ
    -0.20
    spaces
    -0.19
    rn
    -0.18
    UNE
    -0.18
    éĩijä»·
    -0.18
    æĥ´
    -0.18
    ç«ŀäºī
    -0.18
    éĨĮ
    -0.18
     shade
    -0.18
    POSITIVE LOGITS
     Alaska
    0.25
    æ¸ļ
    0.20
    éĿ¢çĽ®
    0.20
    èĹ»
    0.20
    istra
    0.20
    èĭĶ
    0.20
    驼
    0.19
    -mobile
    0.19
    orta
    0.19
    åıijæĮ¥ä½ľçĶ¨
    0.18
    Activations Density 0.003%

    No Known Activations