© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 36628
    Prev
    Next
    INDEX
    Explanations

    online learning and telehealth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
    ç«Ļèµ·æĿ¥
    -0.10
    hek
    -0.09
     collo
    -0.08
    iard
    -0.08
    imen
    -0.08
    deen
    -0.08
    æķĪ
    -0.08
    lij
    -0.08
    imar
    -0.08
    Invoker
    -0.08
    POSITIVE LOGITS
    严èĤĥ
    0.10
    æĪIJçĨŁ
    0.10
    çݯå¢ĥä¸ĭ
    0.09
    è¿ľç¨ĭ
    0.09
    åľ¨çº¿
    0.09
    æĪIJçĨŁçļĦ
    0.09
    饰
    0.08
    æķıéĶIJ
    0.08
    å·´
    0.08
    åĨĪ
    0.08
    Activations Density 0.033%

    No Known Activations