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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 30711
    Prev
    Next
    INDEX
    Explanations

    Category pages

    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
    梯
    -0.09
    .PackageManager
    -0.09
    è³´
    -0.08
    burn
    -0.08
     Dex
    -0.08
    .addListener
    -0.08
    é»İæĺİ
    -0.08
     подпиÑģ
    -0.08
    ä¸ĢæĶ¯
    -0.08
    Mgr
    -0.08
    POSITIVE LOGITS
    wiki
    0.11
    页
    0.10
    è¶ģ
    0.09
    èĪį
    0.09
    æķ´çIJĨ
    0.09
    éĢłç¦ı
    0.09
    Wiki
    0.08
     links
    0.08
     page
    0.08
    ä¸įæĸŃå®ĮåĸĦ
    0.08
    Activations Density 0.215%

    No Known Activations