© 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. 24111
    Prev
    Next
    INDEX
    Explanations

    genius and genus

    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
    oint
    -0.10
    ose
    -0.09
    cker
    -0.09
    zos
    -0.09
    atoon
    -0.08
    agon
    -0.08
    对èĩªå·±
    -0.08
    工夫
    -0.08
    ç»ıåİĨ
    -0.08
    icer
    -0.08
    POSITIVE LOGITS
    åįģ足
    0.12
    å¤ł
    0.09
    é¦ħ
    0.09
    ãģĤãģª
    0.09
    elves
    0.09
    åĭĥåĭĥ
    0.09
    ess
    0.09
    wig
    0.09
    渥
    0.09
    ย
    0.09
    Activations Density 0.002%

    No Known Activations