© 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. 12219
    Prev
    Next
    INDEX
    Explanations

    in the

    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
    çĵľ
    -0.09
    upy
    -0.09
    ummer
    -0.09
    eration
    -0.09
     å¯
    -0.09
    chied
    -0.09
    设æĸ½å»ºè®¾
    -0.09
    称
    -0.08
    æ¥Ļ
    -0.08
    _DISPLAY
    -0.08
    POSITIVE LOGITS
    åIJĮæĹ¶ä¹Łæĺ¯
    0.10
    åĬ²
    0.09
    èĬ±çº¹
    0.08
    å¸ĤæĶ¿åºľ
    0.08
    趴
    0.08
    _ACTIONS
    0.08
    ãĥ¯ãĥ³
    0.08
    æľºä½ĵ
    0.08
    ajes
    0.08
    é£İæĻ¯
    0.08
    Activations Density 0.087%

    No Known Activations