© 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. 15494
    Prev
    Next
    INDEX
    Explanations

    "of" followed by noun

    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
    åģļæ³ķ
    -0.26
    çļĦåģļæ³ķ
    -0.20
    çļĦåºĶçĶ¨
    -0.19
    .opensource
    -0.19
     него
    -0.18
    å°Ĩåħ¶
    -0.17
    åıįèħIJ
    -0.17
    ooks
    -0.17
    aurus
    -0.17
    è¿Ļä¹Īåģļ
    -0.17
    POSITIVE LOGITS
    /testing
    0.25
    /de
    0.24
     certain
    0.23
    æŁIJäºĽ
    0.23
    æľīåħ³
    0.22
    /re
    0.21
    åĴĮå®ĮåĸĦ
    0.21
    æİī
    0.20
    /up
    0.20
    /mod
    0.20
    Activations Density 0.468%

    No Known Activations