© 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. 15436
    Prev
    Next
    INDEX
    Explanations

    hymenopterans

    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
    èł¹
    -0.22
    宵
    -0.21
    inha
    -0.20
     cigarettes
    -0.20
    ç¬ŀ
    -0.20
    _food
    -0.19
    çķĪ
    -0.19
    åİŁæ²¹
    -0.18
    xmm
    -0.18
    gh
    -0.18
    POSITIVE LOGITS
    å§IJ妹
    0.21
    .Actor
    0.20
    åħ³èģĶ交æĺĵ
    0.19
    èĤ¢ä½ĵ
    0.18
    轿
    0.18
    ä¼łåĬ¨
    0.18
     chassis
    0.17
    æŀ¶åŃIJ
    0.17
     gym
    0.17
    åĽ½èµĦå§Ķ
    0.17
    Activations Density 0.641%

    No Known Activations