© 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. 37447
    Prev
    Next
    INDEX
    Explanations

    `story` or `post` after similar terms

    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
    弯
    -0.10
    ç¾Ķ
    -0.10
    åĢ¾æĸľ
    -0.10
    agli
    -0.09
     bent
    -0.09
     closet
    -0.09
    åºĶæľīçļĦ
    -0.08
    çĵ¯
    -0.08
    icker
    -0.08
    çĽİ
    -0.08
    POSITIVE LOGITS
    ä¸Ģç¯ĩæĸĩç«ł
    0.11
    ä½ľåĵģ
    0.11
    æŁIJ个
    0.10
    ä¸Ģç¯ĩ
    0.10
    åħ¬åħ±
    0.09
    .piece
    0.09
    æŁIJ
    0.09
    åĻİ
    0.09
    æĺ¯éĿŀ
    0.09
    æľīæĦıæĢĿçļĦ
    0.08
    Activations Density 0.144%

    No Known Activations