© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35755
    Prev
    Next
    INDEX
    Explanations

    closing brackets after code or markup

    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
    اش
    -0.10
    DataGridViewTextBoxColumn
    -0.09
    棵
    -0.09
    ods
    -0.09
    lyn
    -0.09
    åĿļæŀľ
    -0.09
    elen
    -0.09
    راس
    -0.09
    ately
    -0.09
    inus
    -0.09
    POSITIVE LOGITS
    ãģ¹ãģį
    0.11
    yr
    0.09
    人士
    0.09
    orld
    0.09
    åĪ»æĦı
    0.09
    aron
    0.09
    ãĤ¹ãĥĿ
    0.09
    yı
    0.08
    iro
    0.08
    æ»ĵ
    0.08
    Activations Density 0.308%

    No Known Activations