© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 11581
    Prev
    Next
    INDEX
    Explanations

    offensive and vulgar language

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    åı¯çĸij
    -0.21
    æĴķ
    -0.20
    泯
    -0.19
    æ¯ķ
    -0.19
    opa
    -0.18
    åıijæĺİ
    -0.18
    æ½ľèĥ½
    -0.18
    æĪ¿åŃIJ
    -0.18
    æ³ķå®ĺ
    -0.18
    arf
    -0.18
    POSITIVE LOGITS
    æºħ
    0.20
     или
    0.18
    åįĩ级
    0.18
    Ñģлов
    0.18
     деÑĤÑģк
    0.17
    å¯Įæľī
    0.17
    ªĮ
    0.17
    æĪĸ許
    0.17
     soak
    0.17
     Tits
    0.17
    Activations Density 0.003%

    No Known Activations