© 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. 37064
    Prev
    Next
    INDEX
    Explanations

    Cato scholars

    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
    ä¸Ŀä¸Ŀ
    -0.09
    INGER
    -0.09
    issen
    -0.09
    主åĬ¨
    -0.09
    -place
    -0.08
    åĿļåĽº
    -0.08
    chn
    -0.08
     bầu
    -0.08
    æ°´æĻ¶
    -0.08
    inger
    -0.08
    POSITIVE LOGITS
    æµĵ
    0.09
    ä¸ĢéĿ¢
    0.09
    ucking
    0.08
    妲
    0.08
    ä¸ĢåĪĨ
    0.08
    ä¹ĭéĻħ
    0.08
    lime
    0.08
    éĽį
    0.08
    etta
    0.08
    ical
    0.08
    Activations Density 0.009%

    No Known Activations