© 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. 16055
    Prev
    Next
    INDEX
    Explanations

    season ticket holders

    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
    åīª
    -0.22
    hem
    -0.20
     cop
    -0.20
    ferences
    -0.20
    @qq
    -0.20
     either
    -0.20
    clo
    -0.19
    cop
    -0.19
    ry
    -0.19
    æ´»
    -0.19
    POSITIVE LOGITS
    å®£ä¼łæ´»åĬ¨
    0.20
    erator
    0.20
    accessible
    0.19
    é¢ĦåħĪ
    0.19
    åĩºçĶŁäºİ
    0.18
    çľĭçĤ¹
    0.18
    çŤ
    0.18
    æ¸Ĭ
    0.18
    /WebAPI
    0.18
    éĢīå®ļ
    0.18
    Activations Density 0.014%

    No Known Activations