© 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. 14569
    Prev
    Next
    INDEX
    Explanations

    downloading and uploading

    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
    pret
    -0.23
     pret
    -0.23
    ä¹į
    -0.21
    allet
    -0.20
     Religion
    -0.19
    ppe
    -0.19
     Coke
    -0.19
    geois
    -0.19
    lege
    -0.19
    槿
    -0.19
    POSITIVE LOGITS
    éĢŁåº¦
    0.33
     downloading
    0.28
    é«ĺéĢŁ
    0.28
    éĢŁçİĩ
    0.28
    è¿Ľåº¦
    0.27
    çļĦéĢŁåº¦
    0.27
    ä¸ĭè½½
    0.27
     ÑģкоÑĢоÑģÑĤÑĮ
    0.27
     speed
    0.27
    ä¼łè¾ĵ
    0.26
    Activations Density 0.258%

    No Known Activations