© 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. 7972
    Prev
    Next
    INDEX
    Explanations

    when to use questions

    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
    _closure
    -0.09
    PHY
    -0.09
    uren
    -0.09
    ayed
    -0.09
    ypy
    -0.09
    audi
    -0.08
    gro
    -0.08
    æ·±çŁ¥
    -0.08
    unate
    -0.08
    Hillary
    -0.08
    POSITIVE LOGITS
    abouts
    0.12
    /how
    0.11
    soever
    0.10
    æĺ¯çľŁçļĦ
    0.09
    é»ijå¤ľ
    0.09
    rames
    0.08
    ä¹ĭéĻħ
    0.08
    羣åģĩ
    0.08
    çīĪæĿĥ声æĺİ
    0.08
    ood
    0.08
    Activations Density 0.027%

    No Known Activations