© 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. 12652
    Prev
    Next
    INDEX
    Explanations

    best practices

    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
    综åIJĪå®ŀåĬĽ
    -0.23
    lain
    -0.20
    éĹ¼
    -0.20
    æĴĤ
    -0.19
    åĬłå·¥åİĤ
    -0.19
    èħ¾é£ŀ
    -0.19
    æIJģ
    -0.19
    ниÑĨа
    -0.18
    rael
    -0.18
    ulo
    -0.18
    POSITIVE LOGITS
    æłĩåĩĨ
    0.28
     standards
    0.25
     practices
    0.25
    åģļæ³ķ
    0.25
     standard
    0.24
    åİŁåĪĻ
    0.21
    -standard
    0.21
    åħ¸èĮĥ
    0.21
    çļĦæłĩåĩĨ
    0.20
    åĩĨåĪĻ
    0.20
    Activations Density 0.022%

    No Known Activations