© 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. 35661
    Prev
    Next
    INDEX
    Explanations

    launched

    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
    ities
    -0.09
    è°Ĺ
    -0.09
    è¿ĽæŃ¥
    -0.09
     Staples
    -0.09
    èµĦæºIJæķ´åIJĪ
    -0.09
    ÙĬر
    -0.08
    oki
    -0.08
    éĶĻè¿ĩ
    -0.08
    .flink
    -0.08
    ately
    -0.08
    POSITIVE LOGITS
    äºĨèĩªå·±çļĦ
    0.12
    骥
    0.09
    ãĤį
    0.09
    示æĦı
    0.09
    aine
    0.09
    åħ¨æĸ°çļĦ
    0.09
    egg
    0.08
    backs
    0.08
    çķĻä¸ĭäºĨ
    0.08
    emann
    0.08
    Activations Density 0.018%

    No Known Activations