© 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. 8088
    Prev
    Next
    INDEX
    Explanations

    celestial bodies and their properties

    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
    æģ°å¥½
    -0.10
     mess
    -0.09
    IDD
    -0.09
    æĸĩæĺĮ
    -0.09
    æ¬ºè´Ł
    -0.09
    æ¯Ĵ
    -0.09
    å̦
    -0.09
    鼶è·Ŀ离
    -0.09
    bucks
    -0.08
    éĢļè¡Į
    -0.08
    POSITIVE LOGITS
     stretched
    0.09
    çĽ¸äº²
    0.09
     Stretch
    0.08
    Mirror
    0.08
    _dimension
    0.08
    éī
    0.08
     isol
    0.08
    house
    0.08
    伸
    0.08
    ç¬ijèĦ¸
    0.08
    Activations Density 0.078%

    No Known Activations