© 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. 1182
    Prev
    Next
    INDEX
    Explanations

    kidnapping, abduction, capture, 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
    оÑı
    -0.11
    .appspot
    -0.11
    izin
    -0.09
    alth
    -0.08
    bite
    -0.08
    chn
    -0.08
    ë³ijìĽIJ
    -0.08
    æĭ¨
    -0.08
    ä¸įå¤ļ
    -0.08
    ptr
    -0.08
    POSITIVE LOGITS
    æĭĬ
    0.08
    å»ĵ
    0.08
    è¡Įéķ¿
    0.08
    éģIJ
    0.08
    ç»Łè®¡å±Ģ
    0.08
    оÑī
    0.08
    ä½¥
    0.08
    è¹Ļ
    0.08
    éĺĦ
    0.08
    ëł¥
    0.08
    Activations Density 0.007%

    No Known Activations