© 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. 33559
    Prev
    Next
    INDEX
    Explanations

    ranking or position changes

    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
    è§ŀ
    -0.09
    aisy
    -0.09
    hurst
    -0.08
    窨
    -0.08
    iaux
    -0.08
     Sext
    -0.08
    就好
    -0.08
    æĪ®
    -0.08
    åı£
    -0.08
     strap
    -0.08
    POSITIVE LOGITS
    æĪIJ为
    0.13
    æĪIJ为ä¸ŃåĽ½
    0.11
    跻身
    0.11
    æĪIJ为äºĨ
    0.10
    ç½®æį¢
    0.10
    æĮ¤
    0.10
    æĪIJçĤº
    0.09
     Overnight
    0.09
    é«Ģ
    0.09
    åħ¬åħ±æĸĩåĮĸ
    0.09
    Activations Density 0.019%

    No Known Activations