© 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. 12611
    Prev
    Next
    INDEX
    Explanations

    real-world or real-life contexts

    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
    好åIJ§
    -0.18
    åīįç½®
    -0.18
    ä¸ĢæĿ¡
    -0.18
    æĢ»çĽij
    -0.18
     Sham
    -0.18
    åĴĮæĶ¯æĮģ
    -0.17
    erialize
    -0.17
    mant
    -0.17
    /Branch
    -0.17
    ÑĩÑĢежден
    -0.17
    POSITIVE LOGITS
    -world
    0.22
    (real
    0.22
     scenario
    0.22
    -life
    0.21
    ä¾ĭåŃIJ
    0.20
    ITY
    0.20
    åŃĺåľ¨çļĦ
    0.20
    edata
    0.20
    åıijçĶŁçļĦ
    0.19
    éļĽ
    0.17
    Activations Density 0.046%

    No Known Activations