© 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. 12975
    Prev
    Next
    INDEX
    Explanations

    throwing, flying, off, around, out

    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
    ÑĢей
    -0.21
    æĶĿ
    -0.20
    ä¼ļéķ¿
    -0.20
    èķ¤
    -0.20
    ä¸įå½ĵ
    -0.19
    ä¸įå°ı
    -0.19
    æģĭæĥħ
    -0.18
    æ°ĵ
    -0.18
    gency
    -0.18
    åıĮæīĭ
    -0.18
    POSITIVE LOGITS
    çľ¼åīį
    0.23
     presented
    0.21
     soc
    0.21
    Dos
    0.20
    imon
    0.20
    éĿ¢åīį
    0.20
     Dos
    0.20
    å¼ıçļĦ
    0.20
    èĢĥçĶŁ
    0.20
    antro
    0.19
    Activations Density 0.026%

    No Known Activations