© 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. 54953
    Prev
    Next
    INDEX
    Explanations

    quality of life

    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
    beth
    -0.09
    æ´Ħ
    -0.09
    åIJ¬å¾Ĺ
    -0.09
    ä¸į足
    -0.09
    ugi
    -0.09
    æĬ±åĽ¢
    -0.09
    çĶŁçī©åѦ
    -0.09
    ected
    -0.09
    panic
    -0.08
    PathComponent
    -0.08
    POSITIVE LOGITS
    /environment
    0.09
    _nl
    0.09
    etro
    0.09
    Õ¢
    0.08
    æīĢåľ¨
    0.08
    ä¸ļä½Ļ
    0.08
    èįIJ
    0.08
     اÙĦÙĥرÙĬÙħ
    0.08
    æľīæĦı
    0.08
     enh
    0.08
    Activations Density 0.026%

    No Known Activations