© 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. 21083
    Prev
    Next
    INDEX
    Explanations

    reading books

    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
    æ¯ĶæĪij
    -0.11
    izza
    -0.09
    éĢĴ
    -0.09
    åIJ¸æ¯Ĵ
    -0.09
    ewan
    -0.09
    çĪ¶åŃIJ
    -0.09
    第ä¸ĢæĿ¡
    -0.08
    bast
    -0.08
    åĩłçĤ¹
    -0.08
    afil
    -0.08
    POSITIVE LOGITS
    è¿Ļæľ¬ä¹¦
    0.11
    .book
    0.10
     книги
    0.10
    ä¸Ģæľ¬
    0.09
    书ç±į
    0.09
    æīī
    0.09
    åĽ«
    0.09
     book
    0.09
    ä¸Ģæľ¬ä¹¦
    0.09
    çļĦ身影
    0.09
    Activations Density 0.028%

    No Known Activations