© 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. 55862
    Prev
    Next
    INDEX
    Explanations

    frustration and annoyance

    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
    æģIJ
    -0.11
     scares
    -0.11
    arend
    -0.09
    ç«¿
    -0.09
    åIJĵå¾Ĺ
    -0.09
    æ·±æĥħ
    -0.09
    _atom
    -0.09
    erot
    -0.09
    欢
    -0.09
    人人
    -0.09
    POSITIVE LOGITS
     frustrating
    0.17
     frustration
    0.16
     frustr
    0.15
     frustrated
    0.14
     frustrations
    0.14
     infuri
    0.11
    æĦ¤
    0.11
    æĮ«
    0.10
    çĥ¦
    0.10
    æĮ«æĬĺ
    0.09
    Activations Density 0.038%

    No Known Activations