© 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. 1865
    Prev
    Next
    INDEX
    Explanations

    probability and uncertainty expressions

    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
     Caucus
    -0.09
     ÙĨÙģسÙĩ
    -0.09
     himself
    -0.09
     anale
    -0.08
     dra
    -0.08
    åįĹæĸ¹
    -0.08
    æľ¬èº«çļĦ
    -0.08
    妹
    -0.08
    éĢĢ
    -0.08
    éĹ·
    -0.08
    POSITIVE LOGITS
    æ¦Ĥçİĩ
    0.16
    probability
    0.12
     probability
    0.12
    çļĦæ¦Ĥçİĩ
    0.11
    åĩłçİĩ
    0.11
    æĪIJåĬŁçİĩ
    0.10
    è£ķ
    0.10
    åı¯èĥ½æĢ§
    0.10
    ç»Ŀ大å¤ļæķ°
    0.10
     Probability
    0.10
    Activations Density 0.043%

    No Known Activations