© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12317
    Prev
    Next
    INDEX
    Explanations

    guess and answers

    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
    å®īå®ļ
    -0.19
    浪
    -0.19
    CTL
    -0.18
     æ¸
    -0.18
    mall
    -0.18
    .dd
    -0.18
     Tet
    -0.18
     enc
    -0.18
     pav
    -0.17
     pent
    -0.17
    POSITIVE LOGITS
    æĮijæĪĺ
    0.25
    解çŃĶ
    0.23
    èİŀ
    0.22
    ä¸ī人
    0.21
    íĢ´
    0.21
     guess
    0.21
    å®ĮæĪIJåIJİ
    0.21
    çļĦåĽŀçŃĶ
    0.20
    å°ıä¼Ļä¼´
    0.20
    寮
    0.20
    Activations Density 0.061%

    No Known Activations