© 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. 40141
    Prev
    Next
    INDEX
    Explanations

    well,

    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
    layan
    -0.10
    èĢĮä¸Ķ
    -0.10
    åĴĭ
    -0.09
    uits
    -0.08
    å¨ħ
    -0.08
    ä¹ĭ乡
    -0.08
    èĢĮè¿Ļ
    -0.08
    asel
    -0.08
    å¢ŀå¹ħ
    -0.08
     München
    -0.08
    POSITIVE LOGITS
    åı¯æł¹æį®
    0.10
    olle
    0.10
    ocha
    0.09
    è¯ķè¯ķ
    0.09
    é¦ĸåħĪ
    0.09
    åħ±åIJĮåıijå±ķ
    0.08
    浩
    0.08
    æľķ
    0.08
    ãģªãģĮãĤī
    0.08
    çĪµ
    0.08
    Activations Density 0.014%

    No Known Activations