© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 51787
    Prev
    Next
    INDEX
    Explanations

    box set

    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
    atham
    -0.09
    .px
    -0.09
    oine
    -0.09
    大ä¼ļ
    -0.09
    isse
    -0.08
    Invoker
    -0.08
    cy
    -0.08
    acho
    -0.08
    utex
    -0.08
    omorphic
    -0.08
    POSITIVE LOGITS
    åŃIJéĩĮ
    0.13
    æĻı
    0.12
    -sizing
    0.12
    ÙħÙĤ
    0.10
    .Box
    0.10
    <dyn
    0.10
    åĨħçļĦ
    0.10
    çĽĴåŃIJ
    0.10
    人寿
    0.09
     Boxes
    0.09
    Activations Density 0.055%

    No Known Activations