© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 60766
    Prev
    Next
    INDEX
    Explanations

    cloud storage and file sharing

    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
    Negative Logits
    ç»Į
    -0.10
    zig
    -0.09
    éĢĥè·ij
    -0.09
    çī¡ä¸¹
    -0.09
    _GRAPH
    -0.09
    pare
    -0.09
     Spl
    -0.09
    æĹĮ
    -0.08
    spl
    -0.08
     spl
    -0.08
    POSITIVE LOGITS
    äºij
    0.12
     cloud
    0.11
    cloud
    0.11
    åķĨä¼ļ
    0.10
    äºij端
    0.10
    åij
    0.10
     loft
    0.10
    .Storage
    0.09
    éĽ²
    0.09
     storage
    0.09
    Activations Density 0.171%

    No Known Activations