© 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. 51699
    Prev
    Next
    INDEX
    Explanations

    investigation under oath or guard

    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
    顺åĬ¿
    -0.10
    è½°
    -0.09
    嵩
    -0.09
    otron
    -0.09
    è¤Ĭ
    -0.08
    ifier
    -0.08
    ÙĪÙĬØ©
    -0.08
    heid
    -0.08
    edia
    -0.08
    Dé
    -0.08
    POSITIVE LOGITS
    æĺĤ
    0.10
    çļĦçĶŁåij½
    0.10
     pains
    0.09
    è¨Ĺ
    0.09
    æľĢ好ä¸įè¦ģ
    0.09
    åŃĿ
    0.09
    çĹĽèĭ¦
    0.09
    عت
    0.09
    éĻIJãĤĬ
    0.08
    èµ°è¿ĩ
    0.08
    Activations Density 0.095%

    No Known Activations