© 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. 52013
    Prev
    Next
    INDEX
    Explanations

    zoom in

    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
    éľ²å¤©
    -0.10
    apia
    -0.09
     lightly
    -0.08
     brightly
    -0.08
    æľĢæĹ©çļĦ
    -0.08
    liable
    -0.08
     cust
    -0.08
    æĬĦè¢Ń
    -0.08
    zyst
    -0.08
    umer
    -0.08
    POSITIVE LOGITS
    iore
    0.09
    _TestCase
    0.09
    仪
    0.09
    ç»Ĩ
    0.09
    ä¸Ģè§Ĵ
    0.08
    èģļçĦ¦
    0.08
    ä¸Ģ棵
    0.08
    Wildcard
    0.08
    è¿ĻäºĽéĹ®é¢ĺ
    0.08
    umd
    0.08
    Activations Density 0.018%

    No Known Activations