© 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. 20427
    Prev
    Next
    INDEX
    Explanations

    copyright, development, systems, invalid

    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
    缪
    -0.10
    .gnu
    -0.10
     toy
    -0.09
    uger
    -0.09
    责任æĦŁ
    -0.08
    ç½Ĺæĸ¯
    -0.08
    otor
    -0.08
     Verm
    -0.08
     Cross
    -0.08
    _BIND
    -0.08
    POSITIVE LOGITS
     sting
    0.09
    едÑĮ
    0.09
    dl
    0.09
    è¿Ļç¯ĩ
    0.08
    èĭĹ
    0.08
     scl
    0.08
    æ¸ħæ·¡
    0.08
    å¾Īéķ¿æŶéĹ´
    0.08
    uids
    0.08
    æļĤ
    0.08
    Activations Density 0.031%

    No Known Activations