© 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. 3859
    Prev
    Next
    INDEX
    Explanations

    labor-related suffixes and costs

    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
    amen
    -0.10
    virtual
    -0.09
    yat
    -0.09
    TING
    -0.09
    tlement
    -0.09
    oble
    -0.09
    以ä¾Ĩ
    -0.09
    orris
    -0.09
    讳
    -0.08
    аÑĤелÑĮ
    -0.08
    POSITIVE LOGITS
    mente
    0.12
    iously
    0.10
    ious
    0.10
    fully
    0.10
    èĢħçļĦ
    0.10
    å¯ĨéĽĨ
    0.09
    ogue
    0.09
    à¹Į
    0.09
    ite
    0.09
    rador
    0.09
    Activations Density 0.008%

    No Known Activations