© 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. 59059
    Prev
    Next
    INDEX
    Explanations

    published independently

    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
    åĩºå·®
    -0.12
    绢
    -0.10
    çIJĨåıij
    -0.10
    çľĭçĤ¹
    -0.10
    大åİħ
    -0.09
    ether
    -0.09
    éļĶå£ģ
    -0.09
    å·¥ä½ľæķĪçİĩ
    -0.09
    马æĭī
    -0.09
    é¢Ĩ导å°ıç»Ħ
    -0.09
    POSITIVE LOGITS
    åĩºçīĪ
    0.09
    .margin
    0.09
    åıijå¸ĥçļĦ
    0.08
    对èĩªå·±çļĦ
    0.08
    顺
    0.08
    èĩªå·±
    0.08
     release
    0.08
    åıijå¸ĥ
    0.08
     publish
    0.08
     publication
    0.08
    Activations Density 0.201%

    No Known Activations