© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36164
    Prev
    Next
    INDEX
    Explanations

    asylum seekers

    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
     ÃŃch
    -0.10
    à¤
    -0.09
    ening
    -0.09
    è´ŀ
    -0.09
    å¸Įå°Ķ
    -0.09
    ALTH
    -0.09
    utral
    -0.08
    uctive
    -0.08
    åĦ¿
    -0.08
    istribution
    -0.08
    POSITIVE LOGITS
    èĢħ
    0.10
    pher
    0.09
    akes
    0.09
    otic
    0.09
    è®°å¾Ĺ
    0.09
    èĮĦ
    0.09
    onis
    0.09
     seekers
    0.08
    ander
    0.08
    IED
    0.08
    Activations Density 0.001%

    No Known Activations