© 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. 29709
    Prev
    Next
    INDEX
    Explanations

    species of plant in a family

    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
    禽
    -0.09
    é³ľ
    -0.09
     poultry
    -0.09
    èļķ
    -0.09
    游泳
    -0.09
    èĮ§
    -0.08
    æ¶Į
    -0.08
     Eggs
    -0.08
    æĬ±ä½ı
    -0.08
    å±łå®°
    -0.08
    POSITIVE LOGITS
    èĮİ
    0.16
    æł½åŁ¹
    0.15
    æ¤įçī©
    0.12
    åı¶åŃIJ
    0.12
    çĶŁéķ¿
    0.12
    åı¶çīĩ
    0.12
    ç§įåŃIJ
    0.11
     stem
    0.11
    Plant
    0.10
     Plant
    0.10
    Activations Density 0.221%

    No Known Activations