© 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. 10948
    Prev
    Next
    INDEX
    Explanations

    activities, measurements, or devices

    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
    pth
    -0.19
    æ°´éĩı
    -0.18
    èªĵ
    -0.18
     pragma
    -0.18
    érc
    -0.18
     basal
    -0.18
    被åĬ¨
    -0.18
     Bas
    -0.18
    æĸ¯åŁº
    -0.18
    åĽºå®ļ
    -0.17
    POSITIVE LOGITS
    [](
    0.22
    anean
    0.20
    èĥ¤
    0.20
    abox
    0.20
    uvw
    0.19
    该æ¡Ī
    0.19
    exe
    0.18
    该éĻ¢
    0.18
    UTES
    0.18
    undi
    0.18
    Activations Density 0.639%

    No Known Activations