© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15268
    Prev
    Next
    INDEX
    Explanations

    flour, sand, or architectural elements

    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
    失èIJ½
    -0.20
    oref
    -0.19
    _bounds
    -0.19
     Brace
    -0.18
    ços
    -0.18
    åªĽ
    -0.18
    keit
    -0.18
     à¹Ĩ
    -0.18
    æĬĺæī£
    -0.18
    ós
    -0.18
    POSITIVE LOGITS
    ç»Ļä½łä»¬
    0.18
    å²Ĺ
    0.18
    åıĬ缸åħ³
    0.18
     Cobb
    0.18
    æľīä¸ĢäºĽ
    0.17
    éĩĮéĿ¢
    0.17
    åĽŃ
    0.17
     ruler
    0.17
    å¦Ĥä½ķåİ»
    0.17
    ijľ
    0.17
    Activations Density 0.008%

    No Known Activations