© 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. 16774
    Prev
    Next
    INDEX
    Explanations

    halfway or half-century

    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
    lia
    -0.19
    allis
    -0.19
    PTION
    -0.18
    ection
    -0.17
    ivity
    -0.17
    eer
    -0.17
    hall
    -0.17
    zym
    -0.16
    pery
    -0.16
    urve
    -0.16
    POSITIVE LOGITS
    à¹Ĩ
    0.25
     dozen
    0.22
    个å¤ļ
    0.20
    ãĢħ
    0.20
    ens
    0.20
    ìĶ©
    0.19
    æĥħ人
    0.19
    icap
    0.19
    ridge
    0.19
    åĦ¿
    0.18
    Activations Density 0.019%

    No Known Activations