© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52643
    Prev
    Next
    INDEX
    Explanations

    try out

    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¸Ģçīĩ
    -0.10
    igue
    -0.09
    æĬij
    -0.09
     Tou
    -0.09
     ÐŀÑĩ
    -0.08
     scram
    -0.08
    澡
    -0.08
    åľĨ满å®ĮæĪIJ
    -0.08
    æĮº
    -0.08
    wear
    -0.08
    POSITIVE LOGITS
    ä¿IJ
    0.10
    èħ¿
    0.10
    âĢ¾
    0.09
    èĪIJ
    0.09
     Wings
    0.09
     wings
    0.09
    èģĬèģĬ
    0.09
    æľ¬é¢Ĩ
    0.09
    ç¿°
    0.08
    æīĭèĦļ
    0.08
    Activations Density 0.075%

    No Known Activations