© 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. 32378
    Prev
    Next
    INDEX
    Explanations

    luggage, trunks, and parcels

    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
    éºĴéºŁ
    -0.09
    oram
    -0.09
    åŀ£
    -0.09
    uar
    -0.09
    çīĮåŃIJ
    -0.09
    çݩ游æĪı
    -0.09
    èĥ¡åŃIJ
    -0.09
    ÑĤвеÑĢ
    -0.09
    å·
    -0.09
    ective
    -0.09
    POSITIVE LOGITS
    outer
    0.09
    olini
    0.09
    ynthia
    0.09
    çĻĸ
    0.09
    è¢ĭ
    0.08
    åĨµ
    0.08
    åŀ¢
    0.08
    ANCE
    0.08
    è±¹
    0.08
    mart
    0.08
    Activations Density 0.004%

    No Known Activations