© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12545
    Prev
    Next
    INDEX
    Explanations

    measure of quantity or size

    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
    _PADDING
    -0.20
    åĬ©
    -0.19
    éĤ£æł·çļĦ
    -0.19
    ĪæĿĥ
    -0.19
    æĪĸåħ¶ä»ĸ
    -0.19
     вÑģÑĤÑĢеÑĩ
    -0.18
    并ä¸İ
    -0.18
    è¿ĺæĺ¯ä¼ļ
    -0.18
    OLL
    -0.18
    å¾ĹåĪĨ
    -0.18
    POSITIVE LOGITS
     size
    0.23
    size
    0.23
    çİĩ
    0.22
    éĩı
    0.22
     length
    0.20
    èĮĥåĽ´
    0.20
    umbo
    0.20
    è¹Ļ
    0.20
    åĬĽ
    0.19
    åĪİ
    0.19
    Activations Density 0.177%

    No Known Activations