© 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. 30570
    Prev
    Next
    INDEX
    Explanations

    quantities, measurements, size, value, amount, percentage

    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
    æľĪä¸ĭ
    -0.10
    HING
    -0.09
     unh
    -0.09
    ources
    -0.09
    ä¸į失
    -0.09
     tá»ī
    -0.09
    飫
    -0.09
    å¤ľéĹ´
    -0.09
    orias
    -0.08
     мало
    -0.08
    POSITIVE LOGITS
    strand
    0.09
    为
    0.09
    ris
    0.08
    eration
    0.07
     miracle
    0.07
    æģģ
    0.07
    缸åIJĮçļĦ
    0.07
    umin
    0.07
    lay
    0.07
    umba
    0.07
    Activations Density 0.199%

    No Known Activations