© 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. 13839
    Prev
    Next
    INDEX
    Explanations

    articles followed by definitions

    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
    失败
    -0.24
    æĽ´å¤ļä¿¡æģ¯
    -0.19
    çĪ·
    -0.19
    éªĮè¯ģ
    -0.19
    nice
    -0.18
    Returned
    -0.18
    è¾IJå°Ħ
    -0.18
    ChangeListener
    -0.18
    éĥİ
    -0.18
     اÙĦÙĪاØŃد
    -0.18
    POSITIVE LOGITS
    çļĦä¸Ģç§į
    0.22
    endir
    0.21
    ervised
    0.20
     полÑĮз
    0.20
    aven
    0.20
    <<<<<<<<
    0.20
    ä¸Ģ種
    0.19
    çĽ¸å¯¹è¾ĥ
    0.19
    паÑģ
    0.19
    ä¸Ģç§į
    0.19
    Activations Density 0.249%

    No Known Activations