© 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. 13489
    Prev
    Next
    INDEX
    Explanations

    Joomla CMS development

    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
    Oregon
    -0.25
     Oregon
    -0.21
    Seattle
    -0.20
     confl
    -0.19
     Rockies
    -0.19
    æ¯ĸ
    -0.19
    itten
    -0.19
    fung
    -0.19
    lac
    -0.19
    åī©
    -0.18
    POSITIVE LOGITS
     Joomla
    0.32
    unched
    0.20
    \CMS
    0.20
    æĺŁåħī
    0.20
    OTOR
    0.20
    oomla
    0.19
    UGIN
    0.19
    phan
    0.19
    å®Ľ
    0.18
     Ibrahim
    0.18
    Activations Density 0.066%

    No Known Activations