© 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. 51599
    Prev
    Next
    INDEX
    Explanations

    well wishes and good health

    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
    æķijåij½
    -0.10
    åªĴ
    -0.10
    itive
    -0.09
    æĪı
    -0.09
    大æĪ·
    -0.09
    ç»IJ
    -0.09
    ummy
    -0.09
    abis
    -0.09
    æĹ©æĻļ
    -0.09
    StateException
    -0.08
    POSITIVE LOGITS
    åĵī
    0.09
    åľ¨æķ´ä¸ª
    0.09
    ç¦
    0.08
     continued
    0.08
    åľ¨æľªæĿ¥
    0.08
    æĹ©æĹ¥
    0.08
    åĽŀ头çľĭ
    0.08
     ÑĥÑģпеÑħ
    0.08
     success
    0.08
    èĩ³äºİ
    0.08
    Activations Density 0.003%

    No Known Activations