© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36807
    Prev
    Next
    INDEX
    Explanations

    python script versions

    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
    帼
    -0.12
    èĪįå¾Ĺ
    -0.11
    esco
    -0.11
    enso
    -0.10
    æ±ŁåĮº
    -0.10
    æݨä»ĭä¼ļ
    -0.10
    çĪ±æĬ¤
    -0.10
    è¿Ļå¥Ĺ
    -0.09
    åįĹéĿŀ
    -0.09
    nette
    -0.09
    POSITIVE LOGITS
     Fram
    0.10
    æľīèĩªå·±çļĦ
    0.08
    ÅĦ
    0.08
     replication
    0.07
    rep
    0.07
    AndUpdate
    0.07
    ани
    0.07
     bow
    0.07
    bug
    0.07
     Transmission
    0.07
    Activations Density 0.002%

    No Known Activations