© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 58270
    Prev
    Next
    INDEX
    Explanations

    EPA regulation analysis

    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
    è°¯
    -0.09
    è¿Ļ份
    -0.08
    è¿Ļåľº
    -0.08
    æ³Į
    -0.08
    伤
    -0.08
    æĹłéļľç¢į
    -0.08
    æ·³
    -0.08
    ALT
    -0.08
    请大家
    -0.08
    encies
    -0.08
    POSITIVE LOGITS
    çīĸ
    0.10
    åĨĪ
    0.10
    åľĨå½¢
    0.09
    iglia
    0.09
    éĴ¢éĵģ
    0.09
    çĶŁæĹ¥
    0.09
     Knox
    0.09
     Walnut
    0.09
    çĮİ
    0.09
    åĪ«å¢ħ
    0.09
    Activations Density 0.065%

    No Known Activations