© 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. 36186
    Prev
    Next
    INDEX
    Explanations

    specifically designed

    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
    æŁIJäºĽ
    -0.11
    äºĨ个
    -0.10
    äºĨæĪijçļĦ
    -0.10
    ader
    -0.09
    éĿŀ常å¤ļçļĦ
    -0.09
    äºĨå¾Īå¤ļ
    -0.09
     Certain
    -0.09
    å¾Īå¤ļ
    -0.09
    Certain
    -0.09
    éĵ¸éĢł
    -0.09
    POSITIVE LOGITS
    æĬĬä½ł
    0.15
    æĺ¯ä½ł
    0.14
     yourself
    0.14
    ä¸įè¦ģ太
    0.14
    ä½łçļĦ
    0.13
    çĪ±ä½ł
    0.13
    èĩ³å°ij
    0.13
    ä¸įè¦ģåĨį
    0.12
    å°½åı¯èĥ½
    0.12
    ãģĤãģªãģŁãģ®
    0.12
    Activations Density 0.095%

    No Known Activations