© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12454
    Prev
    Next
    INDEX
    Explanations

    email and message delivery

    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
     wart
    -0.20
    å¿ĥ头
    -0.19
    å·¥ä½ľä¸Ń
    -0.19
     CBC
    -0.19
    åĤ¨å¤ĩ
    -0.19
     Tweets
    -0.19
    èī¯å¥½çļĦ
    -0.18
    è°±åĨĻ
    -0.18
    .blog
    -0.18
    ripe
    -0.18
    POSITIVE LOGITS
    æĿ¥èĩª
    0.20
    issa
    0.19
    ложениÑı
    0.18
    宽带
    0.17
    çļĦåĨħ容
    0.17
    æ¥ļ
    0.17
    å±
    0.17
    åģĩåĨĴ
    0.17
    åĨħ容
    0.17
     landing
    0.17
    Activations Density 0.041%

    No Known Activations