© 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. 20550
    Prev
    Next
    INDEX
    Explanations

    another [noun/adjective]

    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
    æľĢåħ³éĶ®çļĦ
    -0.10
    çļĦä¸ĢåĪĩ
    -0.10
    uffs
    -0.09
    æľīä¸Ģ天
    -0.09
    .realpath
    -0.09
    íĬ¹
    -0.09
    俦
    -0.09
    èĥİ
    -0.09
    çľ¼çľĭ
    -0.09
    çļĦåIJĦç§į
    -0.09
    POSITIVE LOGITS
    è§Ĩ为
    0.09
    ä¹Łæĺ¯ä¸Ģ个
    0.09
    ä¸Ģç¬Ķ
    0.09
    羸
    0.09
    æ¥ŀ
    0.08
    ä¸įéĶĻ
    0.08
    沿线
    0.08
    lobal
    0.08
    åIJĮæł·
    0.08
     excellent
    0.08
    Activations Density 0.018%

    No Known Activations