© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 47736
    Prev
    Next
    INDEX
    Explanations

    Kane Abel Yin Duisburg

    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
    è·ĭ
    -0.09
    è¿Ļ对
    -0.09
    åİ®
    -0.08
    athi
    -0.08
    mit
    -0.08
     Cute
    -0.08
    æŃĮåĶ±
    -0.08
    éŀį
    -0.08
    oucher
    -0.08
    天é¹ħ
    -0.08
    POSITIVE LOGITS
    责任åĪ¶
    0.10
    ess
    0.09
    è·¯ä¸Ĭ
    0.09
    еж
    0.09
    овое
    0.09
    0.09
    ned
    0.09
    hole
    0.08
    åİ¿éķ¿
    0.08
    ingles
    0.08
    Activations Density 0.005%

    No Known Activations