© 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. 38012
    Prev
    Next
    INDEX
    Explanations

    postal codes and numbers

    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¸Ģåı£æ°Ķ
    -0.10
    ç¥ī
    -0.09
    ä¸įæħİ
    -0.09
    两ä¸ī
    -0.08
    çĥĪ
    -0.08
    åįĹæŀģ
    -0.08
    åĽĽäºĶ
    -0.08
     cá»Ń
    -0.08
    à¸Ļาà¸Ļ
    -0.08
    ono
    -0.08
    POSITIVE LOGITS
    åħ·
    0.10
    æ±²
    0.09
    iglia
    0.09
    è£ĻåŃIJ
    0.08
    nga
    0.08
    æIJŃ
    0.08
    ÑĥÑĢÑģ
    0.08
    YPD
    0.08
    åIJŀ
    0.08
     cat
    0.08
    Activations Density 0.057%

    No Known Activations