© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21284
    Prev
    Next
    INDEX
    Explanations

    division championships or tournaments

    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
    é²·
    -0.10
    urt
    -0.09
    èĮ¬
    -0.09
    å±±åİ¿
    -0.08
    çIJ°
    -0.08
    fov
    -0.08
    ITUDE
    -0.08
    datap
    -0.08
    ening
    -0.08
    çijĹ
    -0.08
    POSITIVE LOGITS
    naire
    0.20
    naires
    0.12
    aries
    0.11
    ettes
    0.10
    ÙĬات
    0.10
    IAL
    0.10
    stral
    0.10
    istrator
    0.10
    nement
    0.10
    NEL
    0.10
    Activations Density 0.024%

    No Known Activations