© 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. 1260
    Prev
    Next
    INDEX
    Explanations

    crimes, torture, war crimes

    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
    éĨ®
    -0.10
    å½¢åĬ¿
    -0.09
    æļĿ
    -0.09
    åķĨåѦéĻ¢
    -0.08
    纪念
    -0.08
    å¤ĸçķĮ
    -0.08
    对çŃĸ
    -0.08
    人å¿ĥ
    -0.08
    apper
    -0.08
    èijµ
    -0.08
    POSITIVE LOGITS
    æĭĶ
    0.10
     pant
    0.09
    лав
    0.09
    ä¸ĩæĪ·
    0.09
    ervo
    0.09
    Thin
    0.08
    大è§Ħ模
    0.08
    _DESTROY
    0.08
    çłº
    0.08
     Thin
    0.08
    Activations Density 0.136%

    No Known Activations