© 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. 30212
    Prev
    Next
    INDEX
    Explanations

    swimming gear, archery, tires, viruses, cyclists, cameras, strains

    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
    è¹Ĭ
    -0.08
    Mac
    -0.08
    .tap
    -0.08
    abet
    -0.08
    he
    -0.08
     Boys
    -0.08
    _mac
    -0.08
     SMART
    -0.08
     Jar
    -0.08
    mes
    -0.08
    POSITIVE LOGITS
    奴
    0.11
    tern
    0.10
    ä¸ĵ线
    0.09
    麻çĹ¹
    0.09
    åĿļ
    0.09
    å®ŀçĶ¨æĢ§
    0.09
    ÙħÙģاÙĪضات
    0.09
    ãģ¨ãģĹãģ¦ãģ¯
    0.09
    ÑĤеÑĢ
    0.08
    äºī
    0.08
    Activations Density 0.557%

    No Known Activations