© 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. 51969
    Prev
    Next
    INDEX
    Explanations

    conspiracy, attempts to murder

    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
    æŀķ头
    -0.12
    æĬµæĬĹåĬĽ
    -0.09
    庶
    -0.09
    è£ģ
    -0.08
    _marks
    -0.08
    æıIJæ¡Ī
    -0.08
    åīį线
    -0.08
     HARD
    -0.08
    æĬ¥åijĬ
    -0.08
     requestOptions
    -0.08
    POSITIVE LOGITS
    å¤Ł
    0.09
     Ital
    0.09
    lez
    0.09
    GI
    0.09
    è¿Ļæł·åģļ
    0.09
    å¤ļ人
    0.08
    legg
    0.08
    ä»»ä½ķ人éĥ½
    0.08
    å¾Ĺå¾Ī好
    0.08
    лав
    0.08
    Activations Density 0.002%

    No Known Activations