© 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. 35366
    Prev
    Next
    INDEX
    Explanations

    cap and limits

    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
    åİ»æī¾
    -0.10
    å¢ŀè¿Ľ
    -0.10
     зим
    -0.10
    éĥİ
    -0.09
    æĬĬè¿ĻäºĽ
    -0.09
    swith
    -0.09
    ä¸ĵå¿ĥ
    -0.09
    ç¬Ķè¯ķ
    -0.09
    esser
    -0.09
     ÑģÑĤоÑĢ
    -0.09
    POSITIVE LOGITS
    ä½ıäºĨ
    0.10
    æĭĻ
    0.09
    éĻIJ度
    0.09
     Johan
    0.09
    Reached
    0.09
    å¾Ĺä½ı
    0.09
    庵
    0.08
    æĹı
    0.08
    æĺ¯å¤ļå°ij
    0.08
    LineColor
    0.08
    Activations Density 0.056%

    No Known Activations