© 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. 36259
    Prev
    Next
    INDEX
    Explanations

    billions and trillions

    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
    ders
    -0.10
    ãģ¾ãģĦ
    -0.09
    麻
    -0.09
    tingham
    -0.08
    ellig
    -0.08
    -webpack
    -0.08
    kes
    -0.08
    asted
    -0.08
     Kidd
    -0.08
    /rfc
    -0.08
    POSITIVE LOGITS
    rang
    0.09
    平淡
    0.08
    raf
    0.08
    çĶĦ
    0.08
     gon
    0.08
    corner
    0.08
    æĢİä¹Īæł·
    0.08
    èĮĢ
    0.08
    ron
    0.08
    tron
    0.08
    Activations Density 0.009%

    No Known Activations