© 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. 15072
    Prev
    Next
    INDEX
    Explanations

    mathematics problem sequences

    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
    istani
    -0.20
    ä¸ºæľŁ
    -0.20
    ä¼¼çļĦ
    -0.20
    éī´
    -0.18
    odem
    -0.17
    multipart
    -0.17
    brown
    -0.17
     dönÃ¼ÅŁ
    -0.17
    姹
    -0.17
     Dark
    -0.17
    POSITIVE LOGITS
    ä¸įå¤ļ
    0.20
    GROUND
    0.19
    actively
    0.19
    人家
    0.19
    祢
    0.18
    åİħ
    0.18
    ä¸ĢåĪĢ
    0.18
    (completion
    0.17
    enu
    0.17
    è¶ħè¶Ĭ
    0.17
    Activations Density 0.003%

    No Known Activations