© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7803
    Prev
    Next
    INDEX
    Explanations

    with followed by specifics

    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
    以åıĬåħ¶ä»ĸ
    -0.11
    è¦ģä¸įçĦ¶
    -0.10
     Scalars
    -0.09
    缨
    -0.09
    ãĤ¾
    -0.09
    åĩ¡æľ¬ç½ij
    -0.09
    æĺ¯ä»Ģä¹Īåij¢
    -0.08
    主è¦ģæľī
    -0.08
     демо
    -0.08
    ä¸Ńæľī
    -0.08
    POSITIVE LOGITS
    ç¢į
    0.10
    azen
    0.09
    éĩįå¿ĥ
    0.09
    standing
    0.09
    æ¶īåıĬåĪ°
    0.09
    åı¯éĿłçļĦ
    0.08
    ä»ĺåĩº
    0.08
    纶
    0.08
    leh
    0.08
    ä¸įå¾Ĺä¸į
    0.08
    Activations Density 0.045%

    No Known Activations