© 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. 5987
    Prev
    Next
    INDEX
    Explanations

    application and purchase terms

    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
    çijŀ
    -0.09
    emain
    -0.09
    åįı
    -0.08
    æ»ļåĬ¨
    -0.08
    æħİ
    -0.08
     Recover
    -0.08
    åıĤ
    -0.08
     Merr
    -0.08
    äºĭåħ³
    -0.08
    æĶ¶åĽŀ
    -0.08
    POSITIVE LOGITS
    PerPixel
    0.10
    ä¸įåIJĥ
    0.10
    .bat
    0.10
    çıĤ
    0.09
     BAT
    0.09
    BAT
    0.09
    nist
    0.09
    å¹ħ
    0.09
     pant
    0.09
    京
    0.09
    Activations Density 0.068%

    No Known Activations