© 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. 26366
    Prev
    Next
    INDEX
    Explanations

    bookstore, cinema, and library references

    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
    Not in Any Lists

    No Comments

    Negative Logits
    è£Ļ
    -0.10
    Deposit
    -0.10
    кÑĤ
    -0.09
    åŃĺ款
    -0.08
    .elapsed
    -0.08
    åģļåĪ°äºĨ
    -0.08
    æĽ³
    -0.08
    .easy
    -0.08
    ppard
    -0.08
    è¡į
    -0.08
    POSITIVE LOGITS
    æĮł
    0.12
    èĩªèIJ¥
    0.12
     bookstore
    0.09
    åºĹåĨħ
    0.09
    è¿ŀéĶģ
    0.09
    æĸ°åįİ
    0.09
    æĿĥ
    0.09
    iffe
    0.09
    书åºĹ
    0.08
    isel
    0.08
    Activations Density 0.086%

    No Known Activations