© 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. 56409
    Prev
    Next
    INDEX
    Explanations

    don't need to

    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
    æıŃ
    -0.10
    FetchRequest
    -0.09
    ä¸įèĩ³äºİ
    -0.09
    ogne
    -0.09
    æĥ¬
    -0.09
    便äºİ
    -0.09
    yme
    -0.09
    oving
    -0.09
    åĢº
    -0.08
    cheid
    -0.08
    POSITIVE LOGITS
    fully
    0.10
     prior
    0.10
    lessly
    0.10
    coma
    0.09
    åľ¨æĦı
    0.09
    ä»»ä½ķ
    0.09
     any
    0.08
    åľ¨æł¡
    0.08
     anymore
    0.08
     previous
    0.08
    Activations Density 0.023%

    No Known Activations