© 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. 4835
    Prev
    Next
    INDEX
    Explanations

    expenses claims

    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
    æĦŁåºĶ
    -0.09
    çĤŃ
    -0.09
    泫
    -0.08
    缺å¸Ń
    -0.08
    è¿ĩå¾Ĺ
    -0.08
    åķ¡
    -0.08
    éĢĤåIJĪ
    -0.08
    лÑĥÑĩ
    -0.08
    ifold
    -0.08
    ç´¯
    -0.08
    POSITIVE LOGITS
     mere
    0.11
    ä»ħ为
    0.11
     merely
    0.10
    åįķ纯çļĦ
    0.09
    mere
    0.09
    èĬ±èįī
    0.08
    æŁŀ
    0.08
    æľįåĬ¡äºİ
    0.08
    缮çļĦåľ¨äºİ
    0.08
    åħ¬çĽĬæ´»åĬ¨
    0.08
    Activations Density 0.121%

    No Known Activations