© 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. 13121
    Prev
    Next
    INDEX
    Explanations

    rest of

    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
    ä¸Ģå®ļç¨ĭ度
    -0.20
    åħ¶ä¸Ń
    -0.20
    æŁIJç§į
    -0.20
    æŁIJäºĽ
    -0.20
    åĨį次
    -0.19
    ä¸Ģäºĭ
    -0.18
    åĪĿæľŁ
    -0.18
     different
    -0.18
     litt
    -0.18
     jemand
    -0.18
    POSITIVE LOGITS
    çļĦæŶéĹ´éĩĮ
    0.23
    åIJĥå®Į
    0.21
    /new
    0.20
    Ùħات
    0.19
     Ø£ÙĨØŃاء
    0.19
    çļĦçĪ±æĥħ
    0.19
    most
    0.19
    çļĦåĬ¨ä½ľ
    0.19
    orative
    0.19
    world
    0.18
    Activations Density 0.013%

    No Known Activations