© 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. 26153
    Prev
    Next
    INDEX
    Explanations

    epidemiology, Epstein, epitaxial, epoxy

    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
    -0.09
    eren
    -0.09
    imson
    -0.09
    åĩºåľº
    -0.09
     bè
    -0.09
    活泼
    -0.09
    çİĭçīĮ
    -0.08
    оÑģÑĮ
    -0.08
    ieren
    -0.08
     deepest
    -0.08
    POSITIVE LOGITS
    ILON
    0.11
    ilogue
    0.10
    OND
    0.10
    大èĴľ
    0.09
     hoc
    0.09
    ол
    0.09
    ISODE
    0.09
    entre
    0.08
     Zimmer
    0.08
    ives
    0.08
    Activations Density 0.084%

    No Known Activations