© 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. 1390
    Prev
    Next
    INDEX
    Explanations

    nourishing, trophic, alimentary

    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
    agem
    -0.10
    å±ģ
    -0.10
    oria
    -0.09
     parc
    -0.09
     kiếm
    -0.08
    ALLE
    -0.08
    owe
    -0.08
    lobal
    -0.08
    æł¸å®ŀ
    -0.08
    ekt
    -0.08
    POSITIVE LOGITS
    stoff
    0.12
    è¿ĩåī©
    0.11
     McB
    0.11
    ivot
    0.09
    ful
    0.09
    inging
    0.09
    uess
    0.09
    éĨĮ
    0.09
    lessly
    0.09
    ishment
    0.09
    Activations Density 0.007%

    No Known Activations