© 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. 18080
    Prev
    Next
    INDEX
    Explanations

    how to

    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
    åĬ¨çĶŁæĪIJ
    -0.10
    缮çļĦåľ¨äºİ
    -0.10
    çĦ¶æĺ¯
    -0.10
    شاÙĩ
    -0.10
    око
    -0.10
     ÙĦدÙĬÙĥ
    -0.09
    æĭĽèĤ¡
    -0.09
    ç»ıéªĮ丰å¯Į
    -0.09
    owing
    -0.09
    çŁ¥ä¹İ
    -0.09
    POSITIVE LOGITS
     how
    0.09
    åħ¶ä»ĸ人
    0.08
    ange
    0.08
    让æĤ¨
    0.08
    ä»Ģä¹Īæĺ¯
    0.08
    leck
    0.08
    urre
    0.08
    URRE
    0.08
     ways
    0.08
    å¦Ĥä½ķ
    0.08
    Activations Density 0.025%

    No Known Activations