© 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. 6139
    Prev
    Next
    INDEX
    Explanations

    agency acronyms AFP, AP, AAPL

    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
     kiá»ĩn
    -0.09
    åĬ©æīĭ
    -0.09
    andal
    -0.09
    çĶŁæ¶¯
    -0.08
    çŀĮ
    -0.08
    çIJ¥
    -0.08
    çħ§
    -0.08
    ãģ¾ãģ¾
    -0.08
    ed
    -0.08
    edu
    -0.08
    POSITIVE LOGITS
    鸣
    0.11
     UNUSED
    0.10
     моделÑĮ
    0.09
    .rmi
    0.09
    Reuse
    0.09
    楮
    0.09
    åijľ
    0.09
    prefs
    0.09
    ities
    0.08
    inct
    0.08
    Activations Density 0.006%

    No Known Activations