© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7865
    Prev
    Next
    INDEX
    Explanations

    East Indian colonial British Raj spice routes

    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
    cord
    -0.10
    oram
    -0.10
    æīĭæĮĩ
    -0.10
    enal
    -0.09
    uche
    -0.09
    æĺ¯éŁ©åĽ½
    -0.09
    è¿IJæ°Ķ
    -0.09
     Boehner
    -0.09
    apon
    -0.09
     cord
    -0.09
    POSITIVE LOGITS
    afari
    0.11
    æ®ĸæ°ij
    0.10
     Indies
    0.10
    èĪªæµ·
    0.10
    çĥŃ带
    0.09
     tropical
    0.09
    椰
    0.09
     Tropical
    0.09
     Coconut
    0.09
    èĤ¡æ°ij
    0.09
    Activations Density 0.160%

    No Known Activations