© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 51922
    Prev
    Next
    INDEX
    Explanations

    it does

    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
    wins
    -0.10
    裸
    -0.09
    åıĪ被
    -0.09
    æ¢Ń
    -0.09
    ä¸Ģåı¥è¯Ŀ
    -0.09
    离å¼ĢäºĨ
    -0.09
     teg
    -0.09
    _PCM
    -0.09
    _ALIAS
    -0.09
    è§£æķ£
    -0.08
    POSITIVE LOGITS
     automatically
    0.11
     automáticamente
    0.10
    å¸®ä½ł
    0.10
    ä»İä¸ļ
    0.10
    åĩĨ
    0.10
    èĩªåĬ¨
    0.09
    åijĬè¯īä½ł
    0.09
    å¡«è¡¥
    0.09
    åijĬè¯īæĪij
    0.09
    è·Łä½ł
    0.09
    Activations Density 0.283%

    No Known Activations