© 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. 13167
    Prev
    Next
    INDEX
    Explanations

    use of or as

    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
     hind
    -0.22
    <location
    -0.20
     ever
    -0.20
    enger
    -0.19
    quine
    -0.19
    èĤ¡
    -0.18
     Illustrated
    -0.18
     enumerated
    -0.18
     equ
    -0.17
    arde
    -0.17
    POSITIVE LOGITS
    èĺij
    0.21
     defaulted
    0.21
    æĶ¹éĿ©
    0.21
    æĬļ
    0.20
    ä½ļ
    0.20
    æĪIJ
    0.20
    ANCH
    0.19
    agger
    0.19
     scrap
    0.19
    çļ¿
    0.19
    Activations Density 0.003%

    No Known Activations