© 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. 37357
    Prev
    Next
    INDEX
    Explanations

    easy + description

    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
    è°Īè°Ī
    -0.11
    åIJ®
    -0.10
    ä¸įæŃ»
    -0.10
    è¿ĻäºĽäºº
    -0.09
    technical
    -0.09
    ìĻĦ
    -0.09
     един
    -0.09
    æ¤į
    -0.09
    asio
    -0.09
    HTTPRequest
    -0.09
    POSITIVE LOGITS
     later
    0.09
    åĽŀ头
    0.09
    æ²³
    0.08
    åĴĮæĶ¯æĮģ
    0.08
    åĤ¬
    0.08
    ijke
    0.08
    éĿĴæĺ¥
    0.08
     Bark
    0.08
    later
    0.08
    åĪ°åºķ
    0.08
    Activations Density 0.022%

    No Known Activations