© 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. 63944
    Prev
    Next
    INDEX
    Explanations

    storage area network

    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
    _ELEM
    -0.10
    çĤī
    -0.10
    otre
    -0.09
    模仿
    -0.09
     Maul
    -0.09
    æł·æĿ¿
    -0.09
    çĻ»
    -0.09
    æĸ«
    -0.09
    åľ°éģĵ
    -0.09
     doors
    -0.08
    POSITIVE LOGITS
    ç£ģ
    0.11
     Storage
    0.10
    硬çĽĺ
    0.10
    (storage
    0.09
    åŃĺåĤ¨
    0.09
     Disk
    0.09
    .Storage
    0.09
     ÑħÑĢ
    0.09
    åIJŀåĻ¬
    0.09
     storage
    0.09
    Activations Density 0.253%

    No Known Activations