© 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. 16840
    Prev
    Next
    INDEX
    Explanations

    HTML document beginnings

    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
    ocks
    -0.19
    æĭ¢
    -0.19
    rieb
    -0.19
    lington
    -0.18
    ingly
    -0.18
    eper
    -0.17
    leccion
    -0.16
    pite
    -0.16
    :nil
    -0.16
    iful
    -0.16
    POSITIVE LOGITS
    sWith
    0.20
    UpDown
    0.18
    çł´ç¢İ
    0.17
    å°¼äºļ
    0.17
    ower
    0.17
    DivElement
    0.17
    ä»ħä¾ĽåıĤèĢĥ
    0.17
    å°ı游æĪı
    0.17
    çķĮçļĦ
    0.17
    驽
    0.16
    Activations Density 0.087%

    No Known Activations