© 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. 17536
    Prev
    Next
    INDEX
    Explanations

    architects and design firms

    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
    èĩªæĿ¥
    -0.10
    åŀ¸
    -0.09
    åĴĮ个人
    -0.09
    èĪ¶
    -0.09
     depress
    -0.09
    iska
    -0.09
    毯
    -0.09
    çĶ·
    -0.09
    اÙĦÙĬ
    -0.08
    assel
    -0.08
    POSITIVE LOGITS
    设计
    0.10
    åĽ¢éĺŁ
    0.09
    设计æĸ¹æ¡Ī
    0.09
    建éĢł
    0.09
    odes
    0.08
    _past
    0.08
    æĢ»æī¿åĮħ
    0.08
    é³ŀ
    0.08
     bid
    0.08
    åĭĺå¯Ł
    0.08
    Activations Density 0.048%

    No Known Activations