© 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. 13424
    Prev
    Next
    INDEX
    Explanations

    US senators

    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
    å¥
    -0.20
    åİĤ
    -0.20
    红æĹĹ
    -0.20
    ä¸Ģè¶Ł
    -0.19
    åıįé¦Ī
    -0.19
    kes
    -0.19
    åĬĽè¿ĺæĺ¯
    -0.19
    æĪĪ
    -0.19
    ç»ĵæĻ¶
    -0.19
    åģļé¥Ń
    -0.19
    POSITIVE LOGITS
    è¾¹éĻħ
    0.21
    æĺķ
    0.21
    _lens
    0.19
    _ipc
    0.19
    éħ±
    0.19
    cern
    0.19
     зÑĢениÑı
    0.18
     اÙĦØ¥ÙĨس
    0.18
     TD
    0.18
    æĿŀ
    0.18
    Activations Density 0.001%

    No Known Activations