© 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. 27066
    Prev
    Next
    INDEX
    Explanations

    peripheral embolisation vascular access

    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
    æĺİæĺİ
    -0.10
    ç©ij
    -0.10
    主ä¸ļ
    -0.10
    æ¾ľ
    -0.09
    æĶĴ
    -0.09
    éĺij
    -0.09
    涩
    -0.09
    åĵ¡
    -0.09
    _FAULT
    -0.09
    èIJ¥è¿IJ
    -0.09
    POSITIVE LOGITS
    åİĮ
    0.10
    egas
    0.10
    abinet
    0.09
    çĶŁåij½
    0.09
    å°±ä¸į
    0.08
    èĻı
    0.08
    ä½İä½į
    0.08
    Locker
    0.08
    scatter
    0.08
    æĶ¹éĢł
    0.08
    Activations Density 0.241%

    No Known Activations