© 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. 8893
    Prev
    Next
    INDEX
    Explanations

    correct or resolution or hypothesis

    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
    ä¸įåĬ¨
    -0.10
    åĨįè§ģ
    -0.09
    饯
    -0.09
    误解
    -0.09
    ä¸ŃåĽ½äºº
    -0.08
    é¢ĦæĸĻ
    -0.08
     Highlands
    -0.08
    æŀĦæĢĿ
    -0.08
    cano
    -0.08
    funcs
    -0.08
    POSITIVE LOGITS
    æĬµè¾¾
    0.10
    æĤ¬
    0.09
    å±ıèĶ½
    0.09
    çĺª
    0.08
    åı¯éĿł
    0.08
    åī¿
    0.08
    ä¿¡èµĸ
    0.08
    ç»ıè¿ĩ
    0.08
     provisional
    0.08
    lier
    0.07
    Activations Density 0.084%

    No Known Activations