© 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. 20632
    Prev
    Next
    INDEX
    Explanations

    website, site, page, blog content

    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
    çĸ®
    -0.10
    饱满
    -0.10
    å±Ĥåĩº
    -0.09
    ä¸įæĺ¯ä¸Ģ个
    -0.09
    æľīæŶåĢĻ
    -0.09
    åı£å¾Ħ
    -0.09
    ç¬ijèĦ¸
    -0.09
    èݽ
    -0.09
     Ni
    -0.08
    åŃĺåľ¨äºİ
    -0.08
    POSITIVE LOGITS
    èĩªå·±çļĦ
    0.11
    elu
    0.09
     own
    0.09
    ä¸Ģéģĵ
    0.09
    Ctx
    0.09
    awl
    0.09
    jong
    0.09
    MDB
    0.08
    atars
    0.08
    pd
    0.08
    Activations Density 0.050%

    No Known Activations