© 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. 52264
    Prev
    Next
    INDEX
    Explanations

    email address

    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
    ложен
    -0.09
    ird
    -0.09
    пÑĥÑģк
    -0.09
    è·Ŀ
    -0.09
    ä¸Ģéģĵ
    -0.09
    缮åīį为æŃ¢
    -0.08
    zew
    -0.08
    bie
    -0.08
    对æĬĹ
    -0.08
    ãn
    -0.08
    POSITIVE LOGITS
    etas
    0.09
    åijĬ
    0.09
    æī¿åĬŀ
    0.09
    éĿł
    0.09
    æķ´ä¸ªäºº
    0.09
     коÑĤоÑĢого
    0.09
    åĩŃ
    0.09
    æĸ¹å¼ıè¿Ľè¡Į
    0.09
    çŃ
    0.08
    æĸ¹æīį
    0.08
    Activations Density 0.007%

    No Known Activations