© 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. 8718
    Prev
    Next
    INDEX
    Explanations

    gaming, MK, Kart, Ops, Concepts

    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
    ÑĤек
    -0.10
    æĿł
    -0.10
    åĩłå®¶
    -0.10
    acid
    -0.09
    èĤ©èĨĢ
    -0.09
    管çIJĨåijĺ
    -0.09
    éķIJ
    -0.09
    ruc
    -0.09
    illet
    -0.09
    æľŁæľ«
    -0.09
    POSITIVE LOGITS
    Santa
    0.09
    eti
    0.09
    sters
    0.09
    èµĭ
    0.09
    mates
    0.09
    pel
    0.08
    allel
    0.08
     Prev
    0.08
     Santa
    0.08
     pel
    0.08
    Activations Density 0.002%

    No Known Activations