© 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. 37092
    Prev
    Next
    INDEX
    Explanations

    fled, escape, run away

    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
    entes
    -0.11
    åĨ¤
    -0.09
    è¯ī
    -0.09
    ç³Ļ
    -0.09
     lapse
    -0.09
    è±ģ
    -0.09
    ä¸Ģå®ļèĥ½
    -0.09
    hal
    -0.09
    èĮµ
    -0.09
    è§ŀ
    -0.09
    POSITIVE LOGITS
    ä¹Ķ
    0.11
    fore
    0.08
    psc
    0.08
    é¹Ĭ
    0.08
    æ·ĭ
    0.08
    íĥij
    0.08
    æİIJ
    0.08
    å¿ı
    0.08
     Hyde
    0.08
    ä¸įå°ij
    0.08
    Activations Density 0.016%

    No Known Activations