© 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. 31522
    Prev
    Next
    INDEX
    Explanations

    vendors and suppliers

    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
    anity
    -0.09
    æĥłæ°ij
    -0.08
    itic
    -0.08
    ifter
    -0.08
    åĮ¹
    -0.08
     snap
    -0.08
    ifix
    -0.08
    matcher
    -0.07
    åīįçŀ»
    -0.07
     ÑĤом
    -0.07
    POSITIVE LOGITS
    ä¾ĽåºĶåķĨ
    0.23
     Suppliers
    0.17
     suppliers
    0.17
     supplier
    0.17
    åIJĪä½ľä¼Ļä¼´
    0.16
     Supplier
    0.16
    åIJĪä½ľåħ³ç³»
    0.16
     vendors
    0.15
    .vendor
    0.15
    supplier
    0.15
    Activations Density 0.112%

    No Known Activations