© 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. 40213
    Prev
    Next
    INDEX
    Explanations

    samples or sample orders

    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
    ersed
    -0.09
    ä¸Ģ个个
    -0.08
    á»ĩ
    -0.08
    å±Ī
    -0.08
    orz
    -0.08
     Quar
    -0.08
    æ¯ıä¸Ģ天
    -0.08
     özgü
    -0.08
    éĵ²
    -0.08
    /includes
    -0.08
    POSITIVE LOGITS
    Ñĥв
    0.09
    æīĭæ³ķ
    0.09
    deen
    0.09
    ç¾ļ
    0.09
    骧
    0.09
    rant
    0.08
    æł·çļĦ
    0.08
    èĩ»
    0.08
     дог
    0.08
    _PARAMS
    0.08
    Activations Density 0.016%

    No Known Activations