© 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. 14703
    Prev
    Next
    INDEX
    Explanations

    Michigan Court

    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
    港澳
    -0.22
    ugo
    -0.21
    é¦Ļ港
    -0.21
    ä¸ĬéŨ
    -0.20
    éĿĴå²Ľ
    -0.20
    orta
    -0.19
    ëĿ¼ëıĦ
    -0.18
    æ£ł
    -0.18
    undry
    -0.18
     candidacy
    -0.18
    POSITIVE LOGITS
    Michigan
    0.26
    éĥ¢
    0.22
    ìłĪ
    0.20
    Translated
    0.20
     Michigan
    0.19
    SSIP
    0.19
    ä»Ĩ
    0.19
    omid
    0.18
    éºĿ
    0.18
    inish
    0.18
    Activations Density 0.049%

    No Known Activations