© 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. 40177
    Prev
    Next
    INDEX
    Explanations

    full range of

    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
    åı£æ°Ķ
    -0.09
     Colum
    -0.09
    ä¸Ģéĥ¨åĪĨ
    -0.09
    ooting
    -0.08
     Nets
    -0.08
    ä¸Ģå°ı
    -0.08
    á»ī
    -0.08
    ä¸Ģ群人
    -0.08
    afs
    -0.08
    éĢıæ°Ķ
    -0.08
    POSITIVE LOGITS
     imaginable
    0.09
    peg
    0.09
    çѵ
    0.09
    ç²Ĵ
    0.08
    æĪij们åºĶ该
    0.08
    寿
    0.08
    gorithm
    0.08
    大éĻĨ
    0.08
    åħ¬æ°ij
    0.08
    Ark
    0.08
    Activations Density 0.018%

    No Known Activations