© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 9009
    Prev
    Next
    INDEX
    Explanations

    arches, halls, and entrances

    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
    hen
    -0.11
    å²Ĺ
    -0.10
    累累
    -0.10
    åľ¨éĤ£éĩĮ
    -0.09
    ayo
    -0.09
    祸
    -0.09
    ç´«å¤ĸ
    -0.09
    身æĹģ
    -0.09
    çĸ¥
    -0.08
    妮
    -0.08
    POSITIVE LOGITS
    大åİħ
    0.11
    穹
    0.10
    iar
    0.10
    åIJĬé¡¶
    0.10
    央
    0.09
    åİħ
    0.09
     Ceiling
    0.09
    iete
    0.09
    æĬ¬
    0.08
    æľĭ
    0.08
    Activations Density 0.060%

    No Known Activations