© 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. 50330
    Prev
    Next
    INDEX
    Explanations

    Islamic Republic of Iran

    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
    å¿Ĩ
    -0.11
    å¼ĢéĢļ
    -0.10
    å¡«æĬ¥
    -0.10
    íĻĺ
    -0.10
    èĦ¸é¢Ĭ
    -0.10
    æĪijçĪ±ä½ł
    -0.09
    Ñħодим
    -0.09
    elsea
    -0.09
    骨头
    -0.09
    æ®Ĩ
    -0.09
    POSITIVE LOGITS
    antor
    0.09
    éłĺ
    0.08
    çĭ¼
    0.08
    еÑĩно
    0.08
    overe
    0.08
    æIJŀ
    0.08
    èĭį
    0.08
    lee
    0.08
    æIJĵ
    0.08
    æī«
    0.08
    Activations Density 0.009%

    No Known Activations