© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 27131
    Prev
    Next
    INDEX
    Explanations

    you can redistribute

    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
    ëĦĪ
    -0.09
    éĴĪ
    -0.09
    ousse
    -0.08
    çļĦæĸĩåŃĹ
    -0.08
    æĪIJ为ä¸Ģ个
    -0.08
    æķ¢
    -0.08
    XmlElement
    -0.08
    TRANS
    -0.08
    GLenum
    -0.08
    elig
    -0.08
    POSITIVE LOGITS
    æļ
    0.10
    è¿Ļæīį
    0.09
    reso
    0.09
    pha
    0.09
    æĢ»è§īå¾Ĺ
    0.09
     überh
    0.08
    UPI
    0.08
    \Context
    0.08
     heav
    0.08
    å°ģéĹŃ
    0.08
    Activations Density 0.104%

    No Known Activations