© 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. 799
    Prev
    Next
    INDEX
    Explanations

    leader names and 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
    Negative Logits
    mods
    -0.09
     Mods
    -0.09
    饥饿
    -0.09
    èķ²
    -0.08
    åģĩ
    -0.08
    mant
    -0.08
    æݥ触åĪ°
    -0.08
    Falsy
    -0.08
    æīĺ管
    -0.07
     subtitle
    -0.07
    POSITIVE LOGITS
    åħ¼
    0.12
    ç»ıèIJ¥èĢħ
    0.11
    ız
    0.10
    åĪĽå§ĭ
    0.09
     авÑĤоÑĢ
    0.09
    æ³ķå®ļ代表
    0.09
    头èĦij
    0.09
    å¨ĺ
    0.09
    åĪĽå§ĭ人
    0.09
    æĢ»ç»ıçIJĨ
    0.09
    Activations Density 0.081%

    No Known Activations