© 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. 6038
    Prev
    Next
    INDEX
    Explanations

    honorary and hereditary titles

    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
    é¢ī
    -0.09
    èľĴ
    -0.09
    atrice
    -0.09
    anium
    -0.09
    urat
    -0.08
    å¥Ħ
    -0.08
    ãĥľãĥ¼
    -0.08
    à¹ģà¸ĭ
    -0.08
    ToWorld
    -0.08
    è¯ļæĦı
    -0.08
    POSITIVE LOGITS
    å¸Ń
    0.09
    ocz
    0.09
    agar
    0.09
    秩
    0.09
    åºŁ
    0.09
    è£ĺ
    0.09
    mani
    0.08
    utan
    0.08
    裤
    0.08
    ALAR
    0.08
    Activations Density 0.006%

    No Known Activations