© 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. 52014
    Prev
    Next
    INDEX
    Explanations

    instructions and actions

    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
    stra
    -0.09
    å¥ł
    -0.08
    iki
    -0.08
    ä¹IJæĦı
    -0.08
    ä¸Ńæŀ¢
    -0.08
    edes
    -0.08
    obuf
    -0.07
    ipped
    -0.07
    è¿¥
    -0.07
    å°±è¡Į
    -0.07
    POSITIVE LOGITS
    äºĨè§£æĽ´å¤ļ
    0.11
    ÑĤоÑĢ
    0.10
    getQuery
    0.09
    éĺī
    0.09
    æĮ½
    0.09
    æľĽåİ»
    0.09
    æŁ¥çľĭæĽ´å¤ļ
    0.09
    æīŃ转
    0.09
     deutschland
    0.09
    å»ĵ
    0.09
    Activations Density 0.073%

    No Known Activations