© 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. 31548
    Prev
    Next
    INDEX
    Explanations

    Submitted date

    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
    æĬĬèĩªå·±çļĦ
    -0.08
    çĶ³
    -0.08
    ä¸įçĦ¶
    -0.08
    絡
    -0.08
    èĢĥè¯ģ
    -0.08
    çݦ
    -0.07
    绾
    -0.07
     оÑĤлиÑĩа
    -0.07
     aras
    -0.07
     Doub
    -0.07
    POSITIVE LOGITS
    导读
    0.11
    iju
    0.09
    isy
    0.09
    hub
    0.09
    ä»¥ä¹łè¿ijå¹³
    0.08
    ä¸Ģèīĺ
    0.08
    éĺ¶æ¢¯
    0.08
    åģĩæľŁ
    0.08
    å®ŀè·µä¸Ń
    0.08
    ç½ijå°ıç¼ĸ
    0.08
    Activations Density 1.889%

    No Known Activations