© 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. 48706
    Prev
    Next
    INDEX
    Explanations

    male names followed by surnames

    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
    æľ¬äºº
    -0.09
    iors
    -0.09
    äºĨä¸Ģåľº
    -0.09
    åĸīåĴĻ
    -0.09
    å¸ģ
    -0.09
    bite
    -0.08
    è¯ĹæĦı
    -0.08
    æĤ¸
    -0.08
    å¾Ģå¾Ģä¼ļ
    -0.08
    æĬķ身
    -0.08
    POSITIVE LOGITS
     зан
    0.09
    æĽ¿è¡¥
    0.09
     Receipt
    0.09
    èĬŁ
    0.09
    缮åīį
    0.09
    å°ģéĶģ
    0.08
    arios
    0.08
    ç®Ģ
    0.08
    å¤ĸæı´
    0.08
    inos
    0.08
    Activations Density 0.052%

    No Known Activations