© 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. 14897
    Prev
    Next
    INDEX
    Explanations

    medical terms

    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
     ===>
    -0.20
    afort
    -0.19
    æĤĿ
    -0.18
     MessageLookup
    -0.17
    gorithm
    -0.17
    ANK
    -0.17
    .STATUS
    -0.17
    à¸ķà¸ģ
    -0.17
    éĤ¬
    -0.17
    rica
    -0.16
    POSITIVE LOGITS
    æ½®
    0.21
     viet
    0.20
    ä»ĸèĩªå·±
    0.20
    éĽķåĪ»
    0.19
    é¢Ĩ导å°ıç»Ħ
    0.19
    åĩĦ
    0.18
    emoji
    0.18
     Viet
    0.18
    åIJ¬åIJ¬
    0.18
    mux
    0.17
    Activations Density 1.860%

    No Known Activations