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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 8954
    Prev
    Next
    INDEX
    Explanations

    universities and academic groups

    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
    inand
    -0.09
    atron
    -0.08
    åı°
    -0.08
    çĽĤ
    -0.08
    转åŀĭåıijå±ķ
    -0.08
    ITE
    -0.08
    å¾ħ
    -0.08
     Scar
    -0.08
    éĽª
    -0.08
    头çļ®
    -0.07
    POSITIVE LOGITS
    äºĶå®ĺ
    0.11
    æĸ°è¥¿
    0.10
    åľ¨å¸Ĥåľºä¸Ĭ
    0.10
    éĻĦå±ŀ
    0.10
    工人
    0.10
    åĨħ马
    0.09
    ductive
    0.09
    çŃ
    0.09
    éĤĽ
    0.09
     Raised
    0.09
    Activations Density 0.070%

    No Known Activations