© 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. 59119
    Prev
    Next
    INDEX
    Explanations

    prior to

    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
    semi
    -0.09
    ãĤĮ
    -0.09
    å°ıåŃIJ
    -0.09
    доб
    -0.08
    éģĵçIJĨ
    -0.08
    åĶĽ
    -0.08
    é«ĺå±±
    -0.08
    HEN
    -0.08
    åĿĩåĮĢ
    -0.08
    arda
    -0.08
    POSITIVE LOGITS
    å®ļçĤ¹
    0.09
     ÑģобÑģÑĤвенно
    0.09
    æij¸
    0.09
    æij¸ç´¢
    0.09
    æĪij以为
    0.09
    лож
    0.08
    ä¸ĭä¸ĢæŃ¥
    0.08
    缮åīį为æŃ¢
    0.08
    è®·
    0.08
    gte
    0.08
    Activations Density 0.029%

    No Known Activations