© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6801
    Prev
    Next
    INDEX
    Explanations

    arrest, custody, or law enforcement actions

    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
    ç½¢
    -0.09
    çľī
    -0.09
    å¼ĥ
    -0.09
    rig
    -0.09
    æľīçļĦ
    -0.09
    çķ¸
    -0.09
    мÑı
    -0.09
    _exclude
    -0.09
    ä¸įåħ¬å¹³
    -0.09
    åѤçĭ¬
    -0.09
    POSITIVE LOGITS
    éĢ®æįķ
    0.14
    æĬĵæįķ
    0.11
     arrest
    0.10
     extradition
    0.10
     arresting
    0.09
    åĩ¿
    0.09
    ç«ĭæ¡Ī
    0.09
     imprison
    0.09
    æĭĺçķĻ
    0.09
     cuffs
    0.08
    Activations Density 0.110%

    No Known Activations