© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 11085
    Prev
    Next
    INDEX
    Explanations

    original and innovative approaches

    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
    æīŀ
    -0.08
    ä¸Ģ缴éĥ½æĺ¯
    -0.08
     Spo
    -0.08
    ä¸ĭåİ»
    -0.08
     Blow
    -0.08
    浪费
    -0.07
    çݺ
    -0.07
     ÑĢод
    -0.07
    æĸ¯
    -0.07
    ugg
    -0.07
    POSITIVE LOGITS
    çĭ¬çī¹
    0.23
    çĭ¬çī¹çļĦ
    0.22
    æĸ°é¢ĸ
    0.21
    çļĦçĭ¬çī¹
    0.18
     unique
    0.18
    å¥ĩçī¹
    0.18
    (unique
    0.16
     novel
    0.16
    çĭ¬ä¸ĢæĹłäºĮ
    0.16
    unique
    0.16
    Activations Density 0.090%

    No Known Activations