© 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. 17851
    Prev
    Next
    INDEX
    Explanations

    daily living activities

    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
    å°ģ
    -0.10
    ç±
    -0.10
     ÄijÃŃch
    -0.09
    äºĭåĦ¿
    -0.09
    妻
    -0.09
    çĥĺçĦĻ
    -0.09
    æıIJä¾Ľä¼ĺè´¨
    -0.09
    飧
    -0.09
    è°Ĺ
    -0.09
    ä¸Ģåı·
    -0.09
    POSITIVE LOGITS
    çĿ¡è§ī
    0.12
    饷
    0.10
    ç¢Ĺ
    0.10
    åIJĥçļĦ
    0.10
    åIJĥ
    0.10
    çĿ¡
    0.09
     unm
    0.09
    çIJª
    0.09
    åIJĥé¥Ń
    0.09
    _sleep
    0.09
    Activations Density 0.065%

    No Known Activations