© 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. 11512
    Prev
    Next
    INDEX
    Explanations

    mandelbrot set, scene, render times

    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
    å½Ĵ纳
    -0.09
    读åIJİ
    -0.09
    以为
    -0.08
    æĢľ
    -0.08
    ä¼ij
    -0.08
    ivers
    -0.08
    æŀ¢çº½
    -0.08
    yh
    -0.08
    reek
    -0.08
    åѤåįķ
    -0.08
    POSITIVE LOGITS
     Ging
    0.11
    ILLE
    0.10
     Slow
    0.10
    渲æŁĵ
    0.10
    çīĽ
    0.10
    æħ¢
    0.10
    æĤ¬å´ĸ
    0.10
    èī²å½©
    0.10
    åĭ¾
    0.10
    Slow
    0.09
    Activations Density 0.074%

    No Known Activations