© 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. 52153
    Prev
    Next
    INDEX
    Explanations

    setting records

    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
    lias
    -0.09
    åºŀ
    -0.09
    ideon
    -0.09
    çļĦæĿĥåĪ©
    -0.08
    alias
    -0.08
    око
    -0.08
    éķĿ
    -0.08
    ä¼ij
    -0.08
    lijk
    -0.08
    éĻIJæľŁ
    -0.08
    POSITIVE LOGITS
    bum
    0.10
    èĥĮéĿ¢
    0.10
    ses
    0.09
    ä¸įåı¯
    0.09
    å¤ļ项
    0.09
    人çī©
    0.09
    ogl
    0.09
     Boots
    0.09
    ammu
    0.09
    odor
    0.08
    Activations Density 0.029%

    No Known Activations