© 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. 47408
    Prev
    Next
    INDEX
    Explanations

    foreign scripts and words

    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
    ÑĢоÑģÑĤ
    -0.09
    åħħ
    -0.09
    iola
    -0.08
    èĤĺ
    -0.08
    ä»į
    -0.08
    工夫
    -0.08
    çĶľèľľ
    -0.08
    oller
    -0.08
     ESP
    -0.08
    åĬŀåħ¬æ¥¼
    -0.08
    POSITIVE LOGITS
    大éĻĨ
    0.10
    åIJĮæľŁ
    0.09
    ãģ°
    0.09
    天çĶŁ
    0.09
    tras
    0.09
    пÑĤ
    0.09
    é³Į
    0.09
     пÑĢавила
    0.09
    éªĦåĤ²
    0.09
    ä¸Ģ家
    0.09
    Activations Density 0.041%

    No Known Activations