© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6866
    Prev
    Next
    INDEX
    Explanations

    study group collaborations

    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
    éĻª
    -0.10
    æĮ¡
    -0.10
    ä¸Ģ头
    -0.10
     gó
    -0.09
    éħįéŁ³
    -0.09
    icina
    -0.09
    åĢ¼çıŃ
    -0.09
    /bind
    -0.09
    åįģåĪĨéĴŁ
    -0.09
    _Rel
    -0.09
    POSITIVE LOGITS
    æļ´
    0.09
    venture
    0.08
    åĵĦ
    0.08
     worldwide
    0.08
    åį±éĻ©
    0.08
    èľļ
    0.07
    é£İ湿
    0.07
    åĻİ
    0.07
     collaboration
    0.07
    Tur
    0.07
    Activations Density 0.516%

    No Known Activations