© 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. 12018
    Prev
    Next
    INDEX
    Explanations

    durations of events or media

    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
    .Cookie
    -0.21
    æ£Ĥ
    -0.21
    ạnh
    -0.20
    两天
    -0.20
    nam
    -0.20
    ja
    -0.19
    oret
    -0.19
    礼æĭľ
    -0.18
    EDIA
    -0.18
    Counts
    -0.18
    POSITIVE LOGITS
     Grass
    0.20
    å¼ıçļĦ
    0.19
    ãĢĸ
    0.18
    éī´
    0.18
    éĥģ
    0.18
     trừ
    0.17
    ANDLE
    0.17
    ereal
    0.17
    éĦĻ
    0.17
    çļĦä¹łæĥ¯
    0.17
    Activations Density 0.009%

    No Known Activations