© 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. 2879
    Prev
    Next
    INDEX
    Explanations

    Addresses and locations

    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
    个æĢ§
    -0.09
    ä¸Ģç¬Ķ
    -0.09
    æ²Ĩ
    -0.08
    æĸ°å½¢åĬ¿ä¸ĭ
    -0.08
    å¼Łå¼Ł
    -0.08
    æĥħ绪
    -0.08
    æĥľ
    -0.08
    gb
    -0.08
    åİ®
    -0.08
    嬷
    -0.08
    POSITIVE LOGITS
    赤
    0.10
    ä¹Łä¸įè¦ģ
    0.09
    她说
    0.09
    樱èĬ±
    0.09
    .opensource
    0.09
    üp
    0.09
    zip
    0.09
    .Zip
    0.09
    Ĭ¶
    0.09
    bsite
    0.08
    Activations Density 0.038%

    No Known Activations