© 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. 30688
    Prev
    Next
    INDEX
    Explanations

    disk or drive

    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
    åįł
    -0.11
    éļľ
    -0.11
    å¢Ļä½ĵ
    -0.10
    è¿ĻæĿ¡
    -0.10
    tent
    -0.09
    æ¶ķ
    -0.09
    ä¸Ĭä¸ĭ游
    -0.09
    shed
    -0.09
    段
    -0.09
    èį¯å¸Ī
    -0.09
    POSITIVE LOGITS
     disk
    0.12
     Disk
    0.11
     disks
    0.10
    Disk
    0.10
    åŃĺåĤ¨
    0.10
    ettes
    0.09
     removable
    0.09
    ople
    0.09
    移交
    0.09
    _disk
    0.09
    Activations Density 0.127%

    No Known Activations