© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 1693
    Prev
    Next
    INDEX
    Explanations

    allow anyone, prompting them, allow him, cause the, led surgeons, help the, causes plants, led to, render a, allow families

    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
    ä¸įå®Į
    -0.11
    ä¸įä½ı
    -0.10
    able
    -0.09
     Dow
    -0.09
    å¾Ĺä½ı
    -0.09
    åĵĹ
    -0.09
    ago
    -0.08
    å®´ä¼ļ
    -0.08
    å½ĵä¹ĭ
    -0.08
    åıĺçİ°
    -0.08
    POSITIVE LOGITS
    aska
    0.08
     hm
    0.08
    floating
    0.08
    cheduler
    0.08
    AZY
    0.08
     Thá»ĭ
    0.08
    omp
    0.08
    éĴ§
    0.08
    GCC
    0.08
    ize
    0.08
    Activations Density 0.225%

    No Known Activations