© 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. 24313
    Prev
    Next
    INDEX
    Explanations

    last names

    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
    çĴľ
    -0.10
    å¤ļå¤ļ
    -0.09
    ä¸Ģä¸ĩ
    -0.09
    DTD
    -0.09
    èij¡äº¬
    -0.09
    读åIJİ
    -0.09
    _optional
    -0.08
    è¿ĻæĶ¯
    -0.08
    .jms
    -0.08
    读书
    -0.08
    POSITIVE LOGITS
     Greenville
    0.09
     Globe
    0.08
    essor
    0.08
    urer
    0.08
    mant
    0.08
    çİ°åĩº
    0.08
    league
    0.08
    ä½łä¼ļåıijçİ°
    0.08
    課
    0.08
    èļģ
    0.08
    Activations Density 0.093%

    No Known Activations