© 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. 36263
    Prev
    Next
    INDEX
    Explanations

    Mary's or related names

    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
    åºĻ
    -0.11
    å»Ł
    -0.09
    hsi
    -0.09
    rike
    -0.09
    æķĻèĤ²æķĻåѦ
    -0.09
    empl
    -0.09
    çĶ¨è½¦
    -0.09
    aurus
    -0.09
    çī¹æĿĥ
    -0.09
    ä¸įèµ·
    -0.08
    POSITIVE LOGITS
    اء
    0.10
     fancy
    0.09
     Fancy
    0.09
    è²»
    0.09
    ä¿Ŀè¯ģéĩij
    0.08
    ãĥĥãĥĦ
    0.08
    ancy
    0.08
    cio
    0.08
     коÑĤоÑĢом
    0.08
    满æĦı
    0.08
    Activations Density 0.006%

    No Known Activations