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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6679
    Prev
    Next
    INDEX
    Explanations

    my favorite things

    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
    åIJ«
    -0.11
     Lug
    -0.09
    _MAC
    -0.09
    пп
    -0.09
     allot
    -0.09
    åŁ¹
    -0.09
    æĪIJ为ä¸Ģ个
    -0.09
    Ñīи
    -0.09
    äº
    -0.08
    çīĩéĿ¢
    -0.08
    POSITIVE LOGITS
    鼷
    0.10
    æ°¸ä¹ħ
    0.09
    ä¹ĭä¸Ģ
    0.09
    éĺħ读åħ¨æĸĩ
    0.09
    stown
    0.09
    èѬå¦Ĥ
    0.09
    æĹ¥å¸¸å·¥ä½ľ
    0.09
    è¿Ħä»Ĭ为æŃ¢
    0.08
    umer
    0.08
     permanent
    0.08
    Activations Density 0.045%

    No Known Activations