© 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. 21235
    Prev
    Next
    INDEX
    Explanations

    government actions

    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
    brook
    -0.09
    ç»Ħå§Ķä¼ļ
    -0.08
    åħ¬åı¸ç«łç¨ĭ
    -0.08
    fab
    -0.08
    æ¯Ĵ
    -0.08
    gy
    -0.08
    主åĬŀæĸ¹
    -0.08
     by
    -0.08
    åħļå§Ķ书记
    -0.08
    ibal
    -0.07
    POSITIVE LOGITS
    æĭĹ
    0.11
    locker
    0.10
    illian
    0.10
    zimmer
    0.09
    å°ıå¿ĥ翼翼
    0.09
     Açık
    0.09
    ocy
    0.09
    çłĸ
    0.09
    sic
    0.09
    inne
    0.09
    Activations Density 0.024%

    No Known Activations