© 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. 14775
    Prev
    Next
    INDEX
    Explanations

    rank or sort order

    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
    èĬ®
    -0.22
    enn
    -0.20
    对éĿ¢
    -0.20
    å¤ĩæ¡Ī
    -0.20
    .ident
    -0.18
    .datasource
    -0.18
     Kia
    -0.18
    ä¹Łä¸įä¾ĭå¤ĸ
    -0.18
    åĬ©
    -0.18
    irma
    -0.18
    POSITIVE LOGITS
    æİĴåIJį
    0.23
    =top
    0.23
    æİĴè¡Įæ¦ľ
    0.23
    åīįåĪĹ
    0.22
    èµĽ
    0.21
    GED
    0.21
    æ¦ľåįķ
    0.21
    æİĴåIJį第
    0.20
    æİĴåºı
    0.20
    åĨ²
    0.20
    Activations Density 0.018%

    No Known Activations