© 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. 16926
    Prev
    Next
    INDEX
    Explanations

    Brit, Britt, or British related terms

    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
    erah
    -0.20
    erior
    -0.19
    Ñıд
    -0.18
    geb
    -0.17
    ãĥ³ãĤ°
    -0.17
    åŁĶ
    -0.17
    -thirds
    -0.16
    er
    -0.16
    cription
    -0.16
    hr
    -0.16
    POSITIVE LOGITS
    åĢij
    0.28
    们
    0.23
    å©¿
    0.20
    ney
    0.18
    们éĥ½
    0.18
    ely
    0.18
    ãģŁãģ¡
    0.18
    们çļĦ
    0.18
    isque
    0.17
    åĦ¿
    0.17
    Activations Density 0.008%

    No Known Activations