© 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. 20975
    Prev
    Next
    INDEX
    Explanations

    threat and violence

    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
    é½IJ
    -0.09
    羣çIJĨ
    -0.08
    urm
    -0.08
    好è¿IJ
    -0.08
    课å¤ĸ
    -0.08
    åģıå·®
    -0.08
    çİ°åľº
    -0.08
    èĶļ
    -0.08
     congr
    -0.08
    å»·
    -0.08
    POSITIVE LOGITS
    å¨ģèĥģ
    0.21
    threat
    0.15
     threatened
    0.15
     threats
    0.14
     threat
    0.14
     Threat
    0.13
    æĭħå¿ĥ
    0.13
     threatens
    0.13
    -threat
    0.13
     threaten
    0.12
    Activations Density 0.051%

    No Known Activations