© 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. 13025
    Prev
    Next
    INDEX
    Explanations

    .eth domain names

    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
    ä¼¼
    -0.20
    ä¸
    -0.19
     result
    -0.19
     mant
    -0.19
    da
    -0.19
    .
    -0.19
     cab
    -0.19
    ä¹ĭæīĢ以
    -0.19
    ä¸įå¾Ĺä¸į
    -0.19
     dim
    -0.18
    POSITIVE LOGITS
    ãģĬãģĻãģĻ
    0.25
    ãģĦãĤīãģ£
    0.23
    æİ®
    0.23
    ãĤ¤ãĥ³ãĤ¿ãĥ¼ãĥį
    0.22
     taxp
    0.22
     knull
    0.22
    opolitan
    0.21
    Intialized
    0.21
    ãģ¨ãĤĬãģĤ
    0.21
    'gc
    0.21
    Activations Density 0.041%

    No Known Activations