© 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. 29996
    Prev
    Next
    INDEX
    Explanations

    labor and delivery

    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
    ÑĢаÐ
    -0.10
     обÑıз
    -0.09
    ubby
    -0.09
    çĭłæĬĵ
    -0.09
    виÑĤ
    -0.08
    .snap
    -0.08
     yat
    -0.08
    arium
    -0.08
    èľļ
    -0.08
    ÑĩиÑģÑĤ
    -0.08
    POSITIVE LOGITS
    宫
    0.11
     progress
    0.10
     Labor
    0.10
    Labor
    0.10
     NST
    0.09
     labor
    0.09
    宫殿
    0.09
    .Progress
    0.09
    åºķçĽĺ
    0.09
    otec
    0.09
    Activations Density 0.062%

    No Known Activations