© 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. 8565
    Prev
    Next
    INDEX
    Explanations

    dates and times

    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
    ernel
    -0.11
     лиÑĪÑĮ
    -0.11
    inux
    -0.11
    ãĤĪãģĨãģª
    -0.10
    velopment
    -0.10
    ials
    -0.09
    elcome
    -0.09
    vironment
    -0.09
    ibrary
    -0.09
    å°±åľ¨
    -0.09
    POSITIVE LOGITS
    áIJł
    0.10
    ËĮ
    0.10
    ËĪ
    0.10
    edata
    0.10
    åīįæīĢ
    0.10
    PLE
    0.10
    еÑģп
    0.09
    bidden
    0.09
    transforms
    0.09
    ctrine
    0.09
    Activations Density 0.422%

    No Known Activations