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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19847
    Prev
    Next
    INDEX
    Explanations

    first event since

    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
    AGON
    -0.12
    ument
    -0.10
    æģŃ
    -0.10
    ä¸Ģç¯ĩ
    -0.10
     Bolton
    -0.10
    ï¾ī
    -0.10
    sku
    -0.09
    orz
    -0.09
    ihu
    -0.09
    agon
    -0.09
    POSITIVE LOGITS
    æĦıä¹īä¸ĬçļĦ
    0.10
     повÑĭÑĪен
    0.09
     new
    0.09
     officially
    0.08
     actually
    0.08
     ever
    0.08
    æŃ£å¼ı
    0.08
     нового
    0.08
     uninterrupted
    0.08
    cket
    0.08
    Activations Density 0.080%

    No Known Activations