© 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. 31393
    Prev
    Next
    INDEX
    Explanations

    um or UM

    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
    Ìģ
    -0.11
    lez
    -0.10
    yı
    -0.09
     Orr
    -0.09
    bao
    -0.09
    holder
    -0.09
    INST
    -0.09
    hom
    -0.08
    IED
    -0.08
    çĦĺ
    -0.08
    POSITIVE LOGITS
    èĩ¾
    0.12
    à¸Ĭา
    0.10
    تØŃ
    0.10
    à¹īว
    0.10
    ioni
    0.10
    å´ĩå°ļ
    0.09
    iges
    0.09
    ä¿Ł
    0.09
    kehr
    0.09
    поÑĢ
    0.09
    Activations Density 0.048%

    No Known Activations