© 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. 11535
    Prev
    Next
    INDEX
    Explanations

    hit low

    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
    _HOR
    -0.23
    bestos
    -0.21
    opia
    -0.20
    ç©¿æ¢Ń
    -0.20
     Dayton
    -0.19
    æľīæīĢ
    -0.19
    èѦæĥķ
    -0.19
    å±ı
    -0.19
    _WORLD
    -0.18
     scand
    -0.18
    POSITIVE LOGITS
    .Typed
    0.25
    ç»®
    0.20
    ãģĮãģĤãģ£ãģ¦
    0.18
    æĥ³æĥ³
    0.18
    æĬ½åĩº
    0.17
    åģľçĶµ
    0.17
    phant
    0.17
     Bloom
    0.17
    溢价
    0.17
    Symfony
    0.17
    Activations Density 0.001%

    No Known Activations