© 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. 24307
    Prev
    Next
    INDEX
    Explanations

    comparison with empty string

    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
    Negative Logits
    并ä¸įä¼ļ
    -0.09
    å°½åı¯èĥ½
    -0.08
    å¤ĩ
    -0.08
    ä¸įçĶ¨æĭħå¿ĥ
    -0.08
    缴èĩ³
    -0.08
    é¢Ħå¤ĩ
    -0.08
    ä¸Ńå°ıåѦ
    -0.08
    å¥¥åľ°
    -0.08
    IfNeeded
    -0.08
    unes
    -0.08
    POSITIVE LOGITS
    æľīä»»ä½ķ
    0.11
    æľīå¿ħè¦ģ
    0.10
    å·²ç»ıæĺ¯
    0.09
    rame
    0.09
    hood
    0.08
    rael
    0.08
    ãģĭãģ¤
    0.08
    éĹ°
    0.08
     presence
    0.08
    æ¢Ŀ件
    0.08
    Activations Density 0.853%

    No Known Activations