© 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. 1125
    Prev
    Next
    INDEX
    Explanations

    former [job title/role]

    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
    å¸
    -0.10
    <![
    -0.09
    ÑĢаÑģÑĤ
    -0.09
    åIJ¬å®Į
    -0.09
    èµİ
    -0.09
    èĭĶ
    -0.08
    亲æĥħ
    -0.08
    åīįæīĢæľª
    -0.08
    Portable
    -0.08
    ä¸įåĩº
    -0.08
    POSITIVE LOGITS
    说è¿ĩ
    0.09
     Dawson
    0.09
    æİī
    0.09
    ÂŃt
    0.08
    梢
    0.08
    æįī
    0.08
    å¾Īéķ¿æŶéĹ´
    0.08
     Fowler
    0.08
    éĩijçīĮ
    0.08
    çī¹æĦı
    0.08
    Activations Density 0.037%

    No Known Activations