© 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. 11144
    Prev
    Next
    INDEX
    Explanations

    http or programming constructs

    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
    apo
    -0.21
    æŃ©
    -0.21
    çĤ¹æ»´
    -0.19
    éĸ£
    -0.19
    æł¹æį®ä¸įåIJĮ
    -0.19
    cta
    -0.18
    ÃŃch
    -0.18
    é²ľæ´»
    -0.17
    俾
    -0.17
     kak
    -0.17
    POSITIVE LOGITS
    ogs
    0.22
    ä¸įåIJĮäºİ
    0.20
    .amazon
    0.20
     Philipp
    0.20
    empo
    0.20
     Passed
    0.19
    é¹°
    0.19
     untranslated
    0.19
     неÑģк
    0.19
    è¯łéĩĬ
    0.18
    Activations Density 1.229%

    No Known Activations