© 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. 3577
    Prev
    Next
    INDEX
    Explanations

    transit disruptions and ridership

    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
    侬
    -0.10
    çªģçł´åı£
    -0.10
    ish
    -0.09
    ãģĦãģŁãģł
    -0.09
    çĶŁäº§å·¥èīº
    -0.09
    ãģĦãĤĭ
    -0.09
    è°®
    -0.09
    steen
    -0.09
    é¼»åŃIJ
    -0.09
    oose
    -0.09
    POSITIVE LOGITS
    ively
    0.11
    -minded
    0.10
     minded
    0.09
    dden
    0.09
    ually
    0.09
     nostr
    0.09
    人åı£
    0.09
    cribe
    0.09
    éļ³
    0.09
    captures
    0.09
    Activations Density 0.007%

    No Known Activations