© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36311
    Prev
    Next
    INDEX
    Explanations

    affirmative or informational conversational starters

    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
    滩
    -0.09
    æĺ¥ç§ĭ
    -0.09
    æĶ»åĬ¿
    -0.09
    âĻĤ
    -0.08
    åĨĮ
    -0.08
    åķIJ
    -0.08
    æĭ¦æĪª
    -0.08
    åħīèį£
    -0.08
    /master
    -0.08
    æĸĩæĺĮ
    -0.08
    POSITIVE LOGITS
    没æĥ³åĪ°
    0.08
    å·§åIJĪ
    0.08
    ило
    0.08
    stats
    0.08
    çİ©
    0.08
    æĬĢæľ¯æĶ¯æĮģ
    0.08
    槿
    0.08
    ãģĮãĤī
    0.08
    itives
    0.08
    GRES
    0.08
    Activations Density 0.210%

    No Known Activations