© 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. 10130
    Prev
    Next
    INDEX
    Explanations

    head or probe associated phrases

    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
    tech
    -0.10
    寡
    -0.09
    æ¼Ĩ
    -0.09
    驺
    -0.09
    æī¿è½½
    -0.09
    éĶŃ
    -0.08
    æī¿
    -0.08
     pur
    -0.08
    æ·¡
    -0.08
    usp
    -0.08
    POSITIVE LOGITS
    è´´è¿ij
    0.11
    顾éĹ®
    0.11
    身影
    0.09
    éĽĨ群
    0.09
    社群
    0.09
     cabe
    0.09
    .cluster
    0.09
    鸵
    0.09
    深深çļĦ
    0.09
    身åŃIJ
    0.09
    Activations Density 0.034%

    No Known Activations