© 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. 21108
    Prev
    Next
    INDEX
    Explanations

    eve of holidays or names

    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
    iddle
    -0.10
    ái
    -0.08
    -tier
    -0.08
    omer
    -0.08
    ãģĦãĤĭ
    -0.08
    eros
    -0.08
    essler
    -0.08
    ETA
    -0.08
    ists
    -0.08
    izable
    -0.08
    POSITIVE LOGITS
    uate
    0.11
    SIDE
    0.10
    ãģªãģĮãĤī
    0.10
    emente
    0.09
    usz
    0.09
    DED
    0.09
    åķĨæľº
    0.09
    0.09
    ris
    0.09
     dÃłng
    0.09
    Activations Density 0.005%

    No Known Activations