© 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. 50504
    Prev
    Next
    INDEX
    Explanations

    Deadpool and Tribbles episodes

    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
    人éĹ´
    -0.10
    å²Ń
    -0.09
    车ä¸Ĭ
    -0.09
    erial
    -0.09
    stract
    -0.08
     Vig
    -0.08
    財
    -0.08
    belt
    -0.08
    è´¢çī©
    -0.08
    好人
    -0.08
    POSITIVE LOGITS
    è¯ķçĤ¹
    0.09
    elves
    0.09
     voc
    0.09
    èij«
    0.08
    ALLE
    0.08
    nbsp
    0.08
    .ide
    0.08
    çĶŁç´ł
    0.08
    ampo
    0.08
     carpet
    0.08
    Activations Density 0.031%

    No Known Activations