© 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. 60570
    Prev
    Next
    INDEX
    Explanations

    game studios and publishers

    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
    çªģ
    -0.11
    äºī夺
    -0.09
    温æŁĶ
    -0.09
    éķ«
    -0.09
    çªģå¦Ĥ
    -0.09
    天çĦ¶
    -0.09
    æĦŁ
    -0.09
     игÑĢовÑĭе
    -0.09
    кли
    -0.08
     Ñģезон
    -0.08
    POSITIVE LOGITS
    æľīéĻIJåħ¬åı¸
    0.09
    åħ¬åı¸
    0.09
    æľīéĻIJ责任
    0.09
    åħ¬åı¸åľ¨
    0.09
    enis
    0.09
    åħ¬åı¸å°Ĩ
    0.08
    èį¯ä¸ļ
    0.08
    Loaded
    0.08
    åİŁ
    0.08
    æIJŀ好
    0.08
    Activations Density 0.024%

    No Known Activations