© 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. 11476
    Prev
    Next
    INDEX
    Explanations

    resolution and width x height dimensions

    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
    (stypy
    -0.25
    aison
    -0.22
    jar
    -0.21
    kees
    -0.21
    arin
    -0.21
     Jar
    -0.21
    leys
    -0.20
    asil
    -0.20
     ent
    -0.20
    isclosed
    -0.20
    POSITIVE LOGITS
    åĪĨ辨çİĩ
    0.30
    åħ¼å®¹
    0.25
     resolution
    0.25
    主æµģ
    0.23
    æłĩåĩĨ
    0.23
    æĽ´é«ĺ
    0.22
    æĽ´é«ĺçļĦ
    0.22
    åįłæľīçİĩ
    0.22
    æ¡ĮéĿ¢
    0.22
     strugg
    0.21
    Activations Density 0.056%

    No Known Activations