© 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. 12012
    Prev
    Next
    INDEX
    Explanations

    IDEs and related software development tools

    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
     tal
    -0.22
    è±¹
    -0.21
    幡
    -0.21
     Crow
    -0.20
    èĢ
    -0.20
     recap
    -0.20
     powder
    -0.20
    æŀķ
    -0.19
    ç¾ŀ
    -0.19
    åī¯
    -0.19
    POSITIVE LOGITS
     Sting
    0.20
    Opera
    0.20
     ÑģÑĤÑĢоки
    0.20
    大çģ«
    0.20
    _PKG
    0.20
    .plugins
    0.19
    ople
    0.19
    å¼¹æĢ§
    0.19
     Opera
    0.19
    tube
    0.19
    Activations Density 0.067%

    No Known Activations