© 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. 34684
    Prev
    Next
    INDEX
    Explanations

    earned run average

    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
    çŀ§
    -0.11
    æĥ«
    -0.10
    ä¸ĥ大
    -0.09
    ç½¢
    -0.08
    orno
    -0.08
    æľīçļĦ人
    -0.08
    .getClassName
    -0.08
    adro
    -0.08
     NIC
    -0.08
    ldr
    -0.08
    POSITIVE LOGITS
    èİ«æĸ¯
    0.10
     Stout
    0.09
    éģ®
    0.09
     Dud
    0.09
    æ±IJ
    0.08
    æ¼ı
    0.08
    /share
    0.08
     Manufact
    0.08
    æĵ¦
    0.08
    è´¥
    0.08
    Activations Density 0.060%

    No Known Activations