© 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. 16064
    Prev
    Next
    INDEX
    Explanations

    enterprise applications and solutions

    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
    otch
    -0.20
    èĩªæĦ¿
    -0.20
    å±ĭåŃIJ
    -0.19
    æĪij以为
    -0.19
    çī¹èī²å°ıéķĩ
    -0.19
    iciel
    -0.18
    å¾ĹæĦı
    -0.18
    å²Ķ
    -0.18
    ä¸ĺ
    -0.18
    å²Ń
    -0.18
    POSITIVE LOGITS
    级
    0.34
    级åĪ«çļĦ
    0.34
    -grade
    0.30
    -level
    0.29
    级åĪ«
    0.25
    æĽ´å¼º
    0.25
     level
    0.24
    -scale
    0.24
    level
    0.23
    -wide
    0.23
    Activations Density 0.044%

    No Known Activations