© 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. 37103
    Prev
    Next
    INDEX
    Explanations

    jury verdict or allegation

    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
    æĥŃ
    -0.09
    为æ°ij
    -0.09
    åĢ¾
    -0.09
    ayne
    -0.08
    bing
    -0.08
     беÑģп
    -0.08
    åİĨ
    -0.08
    æĺĮ
    -0.08
    atan
    -0.08
     rig
    -0.07
    POSITIVE LOGITS
    æ¸ħæ·¡
    0.11
    éħįä¸Ĭ
    0.10
    æ¸ļ
    0.09
    å§ijå¨ĺ
    0.09
    èµĦæĸĻæĺ¾ç¤º
    0.09
     повеÑĢ
    0.09
    æįı
    0.09
    Ẩ
    0.09
    鼯
    0.09
    ç´¢èµĶ
    0.09
    Activations Density 0.036%

    No Known Activations