© 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. 12554
    Prev
    Next
    INDEX
    Explanations

    variations and narrow ranges

    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
    è¶ĬæĿ¥è¶Ĭå¤ļ
    -0.23
    .pattern
    -0.21
    æ®ĥ
    -0.20
    éªĹåıĸ
    -0.20
    åı¤æĢª
    -0.20
    éħī
    -0.19
    空åīį
    -0.19
    _ADAPTER
    -0.19
    ENTRY
    -0.19
    è¿ĽåŁİ
    -0.18
    POSITIVE LOGITS
    éļıæŶ
    0.33
    éļ¨æĻĤ
    0.28
    éļıæŶéļıåľ°
    0.25
    èĦĨå¼±
    0.24
    çļĦè·Ŀ离
    0.22
    便ä¼ļ
    0.22
     tipping
    0.22
    utan
    0.21
    èѦ
    0.21
     easily
    0.21
    Activations Density 0.119%

    No Known Activations