© 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. 2680
    Prev
    Next
    INDEX
    Explanations

    names like Kris or surnames like Criswell

    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
    sek
    -0.10
    度
    -0.09
    нÑĮ
    -0.08
    mates
    -0.08
    .bd
    -0.08
    绵
    -0.08
     Clerk
    -0.08
    ä¸Ńæĸ°
    -0.08
    ÙĪØ·
    -0.08
    oples
    -0.08
    POSITIVE LOGITS
    åĩłçĤ¹
    0.11
    æ·ŀ
    0.10
    entric
    0.10
    little
    0.10
    oil
    0.10
     little
    0.09
    å¿ĥ头
    0.09
    æ¬ĬçĽĬ
    0.09
    æĿĥçĽĬ
    0.09
    æ±²
    0.09
    Activations Density 0.003%

    No Known Activations