© 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. 2809
    Prev
    Next
    INDEX
    Explanations

    evil, destruction, immorality, false beliefs

    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
     roundup
    -0.09
    æī®
    -0.09
    æľı
    -0.09
    åīįåįģ
    -0.09
    åħį责声æĺİ
    -0.08
     Pills
    -0.08
     Sands
    -0.08
    è´Łè´£ä»»
    -0.08
    Tweet
    -0.08
    è°ĥ
    -0.08
    POSITIVE LOGITS
    ä¸Ģåľº
    0.10
    é¢ł
    0.10
    äºĨä¸Ģåľº
    0.10
    æ²½
    0.09
    è¹ī
    0.09
    èĻļåģĩ
    0.08
    éĥİ
    0.08
    /utility
    0.08
    æīĵéĢļ
    0.08
    ç³Ł
    0.08
    Activations Density 0.038%

    No Known Activations