© 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. 9326
    Prev
    Next
    INDEX
    Explanations

    Brokeback Mountain, Acorn squash, Moonrise Kingdom

    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
    é¢ł
    -0.10
    åİŁæĿIJæĸĻ
    -0.09
    è°£
    -0.09
    çĭĤ
    -0.08
    æģ¯
    -0.08
    ä¸Ģè½®
    -0.08
    çĽ²
    -0.08
    èĢĢ
    -0.08
    欺
    -0.08
    xdb
    -0.08
    POSITIVE LOGITS
    åįĹ京
    0.10
    å®ĩå®Ļ
    0.09
     PropertyValue
    0.09
    åIJijåīį
    0.09
    PropertyValue
    0.09
    ä»İäºĭ
    0.09
    çĭ®åŃIJ
    0.09
    èŀįåĮĸ
    0.09
    ohan
    0.09
    æ¿ł
    0.09
    Activations Density 0.002%

    No Known Activations