© 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. 13444
    Prev
    Next
    INDEX
    Explanations

    trains and related topics

    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
    åľ¨ç½ijä¸Ĭ
    -0.18
    teen
    -0.18
    æĺĻ
    -0.16
    éĨį
    -0.15
    teenth
    -0.15
    ../../../
    -0.15
    æݨèįIJéĺħ读
    -0.15
    é²ľè¡Ģ
    -0.15
    aleb
    -0.15
    åľ¨è·¯ä¸Ĭ
    -0.15
    POSITIVE LOGITS
    ees
    0.23
    ä¹İ
    0.20
    iac
    0.19
     меÑĤÑĢо
    0.19
    åĦ¿
    0.18
    lords
    0.18
    ments
    0.17
    迹
    0.17
    matic
    0.17
    hart
    0.17
    Activations Density 0.016%

    No Known Activations