© 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. 21008
    Prev
    Next
    INDEX
    Explanations

    game lineup, defensive, numbers, boots, books

    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
    广éĺĶçļĦ
    -0.10
    æĻķ
    -0.09
    unga
    -0.09
    å¾Ĵ
    -0.09
    arme
    -0.08
     spectral
    -0.08
    åħ¬çĦ¶
    -0.08
    æĺİ亮
    -0.08
    .setLevel
    -0.08
    transparent
    -0.08
    POSITIVE LOGITS
    oader
    0.10
    ä¸Ģ身
    0.10
    æIJŃéħį
    0.09
    <![
    0.09
     niche
    0.09
    è£ħè½½
    0.09
    ä¸įç®¡ä½ł
    0.09
    é©°
    0.09
    Ãłi
    0.08
     ÑģоÑĩеÑĤ
    0.08
    Activations Density 0.032%

    No Known Activations