© 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. 20122
    Prev
    Next
    INDEX
    Explanations

    baseball teams Cubs, Mets, Astros

    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
    ä¼ļéķ¿
    -0.09
    fare
    -0.09
    fully
    -0.09
    uÃŃ
    -0.08
    forth
    -0.08
    éĽĨåĽ¢èĤ¡ä»½
    -0.08
    pred
    -0.08
    ä¹ĭéģĵ
    -0.08
    baugh
    -0.08
    hip
    -0.08
    POSITIVE LOGITS
    人家
    0.12
    èĸĦ
    0.10
     Scouts
    0.10
    anh
    0.09
    ðŁı»
    0.09
    /small
    0.09
    /tiny
    0.09
    /licenses
    0.09
    çĶ¦
    0.09
    rika
    0.08
    Activations Density 0.004%

    No Known Activations