© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 64121
    Prev
    Next
    INDEX
    Explanations

    has a

    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
    Negative Logits
    åĴĮå°ļ
    -0.09
    æĦŁåºĶ
    -0.09
    ä»ĸæĽ¾
    -0.09
    奸
    -0.08
    iva
    -0.08
    诤
    -0.08
    åħħå®ŀ
    -0.08
    äºĨä»ĸçļĦ
    -0.08
    ippers
    -0.08
    opus
    -0.08
    POSITIVE LOGITS
    amble
    0.09
    ellan
    0.09
    -vers
    0.09
    dk
    0.08
     Toolbox
    0.08
    RK
    0.08
    aign
    0.08
    ERING
    0.08
    uyen
    0.08
    compiler
    0.08
    Activations Density 0.054%

    No Known Activations