© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7956
    Prev
    Next
    INDEX
    Explanations

    abolition and emancipation

    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
    raud
    -0.10
    ãĥIJãĥ³
    -0.10
    ields
    -0.09
    æĪIJéķ¿ä¸º
    -0.09
    Sa
    -0.09
    ä¸ªé¡¹çĽ®
    -0.09
     Strait
    -0.09
    æ°¨åŁº
    -0.09
    ç¼ij
    -0.09
    <Props
    -0.08
    POSITIVE LOGITS
    URI
    0.09
    ist
    0.09
    sst
    0.09
    kart
    0.09
    splash
    0.09
     lẫn
    0.09
    _WRONG
    0.08
    èĥĦ
    0.08
    åŃĹ第
    0.08
    bie
    0.08
    Activations Density 0.006%

    No Known Activations