© 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
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37441
    Prev
    Next
    INDEX
    Explanations

    keep in place

    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
    สา
    -0.10
    çĿ¨
    -0.09
    æĬĬè¿ĻäºĽ
    -0.09
    ãģ®ä¸Ń
    -0.09
    å¤ĩçĶ¨
    -0.09
    åĪĩãĤĮ
    -0.08
    èĮŃ
    -0.08
    elas
    -0.08
    è¿ĿèĥĮ
    -0.08
    west
    -0.08
    POSITIVE LOGITS
    ä½į
    0.09
    ATAR
    0.09
    ê³³
    0.09
    å°ī
    0.09
    awns
    0.09
    é²ľèĬ±
    0.09
    çĭĤ
    0.08
     Commod
    0.08
    ãģ¾ãģ¾
    0.08
    ä¸įåĬ¨
    0.08
    Activations Density 0.079%

    No Known Activations