© 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. 9147
    Prev
    Next
    INDEX
    Explanations

    images and descriptions

    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
    .nih
    -0.09
     ÑĢож
    -0.09
    æŃĮ声
    -0.09
    inidad
    -0.09
    æIJħæĭĮ
    -0.09
    åĪĢ
    -0.09
    зна
    -0.09
    ä¸ĢåĪĢ
    -0.09
    åħįç¨İ
    -0.09
    æī¶
    -0.08
    POSITIVE LOGITS
    _listing
    0.10
     images
    0.10
    æݨä»ĭ
    0.09
    æīĢæľīæĿĥ
    0.09
    åıĤè§Ĥ
    0.09
    产æĿĥ
    0.09
    éĩī
    0.09
    åĩĢåĢ¼
    0.09
     itemprop
    0.09
    Property
    0.09
    Activations Density 0.169%

    No Known Activations