© 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. 11170
    Prev
    Next
    INDEX
    Explanations

    maid, nanny, chef, employed

    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
    èµ
    -0.09
    ãģĵ
    -0.08
     GRE
    -0.08
     gre
    -0.08
     diss
    -0.08
     booths
    -0.08
    çĥŁèįī
    -0.08
    åİĮ
    -0.08
    tracts
    -0.08
     miner
    -0.08
    POSITIVE LOGITS
    ä½£
    0.15
    ä¿Ŀå§Ĩ
    0.14
    ä»Ĩ
    0.14
    éĽĩä½£
    0.14
     maid
    0.13
     nanny
    0.12
    éĺ¿å§¨
    0.12
     hired
    0.12
    maid
    0.11
    çĶ¨å·¥
    0.11
    Activations Density 0.076%

    No Known Activations