© 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. 9656
    Prev
    Next
    INDEX
    Explanations

    common acronyms and abbreviations

    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
     лиÑĪÑĮ
    -0.12
     dạng
    -0.10
    ÑģÑı
    -0.09
    ovel
    -0.09
    uro
    -0.09
    éĻ¬
    -0.09
    ffect
    -0.09
    atch
    -0.09
     kone
    -0.08
     Cá»Ļng
    -0.08
    POSITIVE LOGITS
    busters
    0.11
    обÑĢаз
    0.10
    ification
    0.09
    ivity
    0.09
    å°ª
    0.09
    IED
    0.09
    icy
    0.09
    ë¹Ļ
    0.09
    itory
    0.09
    cion
    0.09
    Activations Density 0.417%

    No Known Activations