© 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. 21143
    Prev
    Next
    INDEX
    Explanations

    explains why or what

    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
    _LL
    -0.09
    éĿŀ常åĸľæ¬¢
    -0.09
    æĪijèĩªå·±
    -0.08
    ä¹Łæĺ¯éĿŀ常
    -0.08
     myself
    -0.08
    sm
    -0.08
    姥
    -0.08
    æ¸ij
    -0.08
    ç¼İ
    -0.08
    0
    -0.08
    POSITIVE LOGITS
    çľĭçľĭ
    0.10
    èģĬèģĬ
    0.10
    æĿ¥çľĭçľĭ
    0.09
    è¡ĮåĪĹ
    0.09
    æľīåĵªäºĽ
    0.09
    EventHandler
    0.09
    missive
    0.09
    åIJ¬åIJ¬
    0.09
     discusses
    0.09
    å¨ĵ
    0.09
    Activations Density 0.189%

    No Known Activations