© 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. 62680
    Prev
    Next
    INDEX
    Explanations

    on foot

    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
    ANCH
    -0.10
    çļĦæĪ¿åŃIJ
    -0.10
    nap
    -0.09
    çĤ¹åįĬ
    -0.09
    éĥ¢
    -0.09
    ç¾ļ
    -0.09
    gett
    -0.09
     liá»ĩt
    -0.09
    icer
    -0.09
    æ´ŀ
    -0.09
    POSITIVE LOGITS
    æĸĭ
    0.11
    å¿ĹæĦ¿
    0.08
    åºĶ注æĦı
    0.08
    éĴ¿
    0.08
    éĹ´çļĦ
    0.08
    çĪ¿
    0.08
    éĹ´
    0.08
     sponsorship
    0.08
    åķľ
    0.08
    roe
    0.08
    Activations Density 0.049%

    No Known Activations