© 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. 14359
    Prev
    Next
    INDEX
    Explanations

    distances and measurements

    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
    æݨéĢģ
    -0.19
    chine
    -0.19
    éħ¿éħĴ
    -0.18
    vtk
    -0.18
    icy
    -0.18
    amus
    -0.18
    ä»ĸä»¬åľ¨
    -0.17
    èĬ¨
    -0.17
    reo
    -0.17
    èĵ
    -0.17
    POSITIVE LOGITS
    spy
    0.25
    ä¸Ģ个æĺŁæľŁ
    0.20
    èģĶåIJĪä¼ļ
    0.20
    akov
    0.20
     Singleton
    0.19
    å½·
    0.19
    åIJ¡
    0.18
    éĶ¦æłĩ
    0.17
    æķıæį·
    0.17
    ç§ĺ书éķ¿
    0.17
    Activations Density 0.015%

    No Known Activations