© 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. 55789
    Prev
    Next
    INDEX
    Explanations

    pursuing or chasing

    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
    صÙĨ
    -0.11
    è¿ĩ渡
    -0.10
    æĮ¥æīĭ
    -0.09
    åıĸãĤĬ
    -0.09
    éĢīæĭĶ
    -0.09
    æĶ¾çľ¼
    -0.09
    ä¸İæŶ
    -0.09
    Ùħد
    -0.08
    èĢĥéªĮ
    -0.08
     Rivera
    -0.08
    POSITIVE LOGITS
    追
    0.16
    踪
    0.13
    线索
    0.12
    足迹
    0.12
    追éĢIJ
    0.12
    追踪
    0.11
     pursued
    0.11
     pursuing
    0.11
     chase
    0.11
     elusive
    0.11
    Activations Density 0.035%

    No Known Activations