© 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. 16592
    Prev
    Next
    INDEX
    Explanations

    youtube video links or css font urls

    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
    sen
    -0.22
    å¿į
    -0.20
    ende
    -0.19
    unter
    -0.18
     Correspond
    -0.18
    sold
    -0.17
    istry
    -0.17
    cape
    -0.17
    erner
    -0.17
    ist
    -0.17
    POSITIVE LOGITS
    bé
    0.21
    _driver
    0.19
    æĪIJé¾Ļ
    0.19
     treat
    0.18
    çķĮå®ļ
    0.18
     inverted
    0.18
    abilities
    0.17
    身æĿIJ
    0.17
    æĤ¬å¿µ
    0.17
    .default
    0.17
    Activations Density 0.003%

    No Known Activations