© 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. 5010
    Prev
    Next
    INDEX
    Explanations

    knowledgeable and informative

    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
    æĦıæĢĿ
    -0.09
    ãģĿãĤĮãģ«
    -0.08
    稳
    -0.08
    æĭ¢
    -0.08
    stead
    -0.08
    ä¸ĩ人
    -0.08
    ãģ¹
    -0.08
    åŁİå¸Ĥ
    -0.08
     Studios
    -0.08
    主ä¹īèĢħ
    -0.08
    POSITIVE LOGITS
    ä¸ĵä¸ļçŁ¥è¯Ĩ
    0.11
    /power
    0.11
    èĥ½åĬĽå¼º
    0.10
    æľīèĥ½åĬĽ
    0.09
    æĨ¬
    0.09
    è¡Įä¸ļ
    0.09
    沿海
    0.09
    ç¦ĺ
    0.09
    éģIJ
    0.09
    .Invoke
    0.09
    Activations Density 0.010%

    No Known Activations