© 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. 11979
    Prev
    Next
    INDEX
    Explanations

    past times and prior eras

    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
    è¡ĮåĬ¨è®¡åĪĴ
    -0.24
    ä¸ī家
    -0.22
    åĿ¨
    -0.20
    $out
    -0.20
    ä¿ĥæĪIJ
    -0.20
    ç»ĪçĶŁ
    -0.20
    åĢĺ
    -0.20
    è¿Ħä»Ĭ为æŃ¢
    -0.20
    å´´
    -0.20
     вним
    -0.19
    POSITIVE LOGITS
    æŶåĢĻ
    0.25
    æĻĤåĢĻ
    0.25
    times
    0.24
     times
    0.23
     days
    0.22
    æĹ¶æľŁçļĦ
    0.22
     before
    0.22
    éĤ£ä¸ªæŶåĢĻ
    0.22
    (before
    0.22
    è¾īçħĮ
    0.21
    Activations Density 0.044%

    No Known Activations