© 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. 18431
    Prev
    Next
    INDEX
    Explanations

    occupy, crowds, turnout, part

    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
    studio
    -0.08
    omat
    -0.08
     Studio
    -0.08
    ç«ŀæĬĢ
    -0.08
    Studio
    -0.08
    æīĵçĮİ
    -0.08
    èĽĽ
    -0.08
    åħľ
    -0.08
    çIJĨ
    -0.08
    åºĸ
    -0.08
    POSITIVE LOGITS
    æŃĮ声
    0.11
    æķ°çĻ¾
    0.11
    çİ°åľº
    0.11
    æ´»åĬ¨çİ°åľº
    0.10
    åľ¨çİ°åľº
    0.10
    临æŶ
    0.10
    åľºåľ°
    0.10
    ikal
    0.10
    æľ¬æ¬¡æ´»åĬ¨
    0.10
    åıĤä¸İèĢħ
    0.10
    Activations Density 0.083%

    No Known Activations