© 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. 14495
    Prev
    Next
    INDEX
    Explanations

    broadcasting media

    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
    æĭĻ
    -0.20
     VID
    -0.19
     filming
    -0.19
    紧迫
    -0.19
    æijĦåĥı
    -0.19
    imary
    -0.18
    èĸ®
    -0.18
    ÑĤелÑĮ
    -0.18
    çĶ·ä¸»
    -0.18
    VID
    -0.17
    POSITIVE LOGITS
    Kansas
    0.22
    åIJ¬ä¼Ĺ
    0.22
    åħ¬è·¯
    0.21
    åľ¨åħ¨åĽ½
    0.21
    é¢ijçİĩ
    0.20
     toll
    0.20
    车载
    0.20
    avo
    0.19
     tick
    0.19
     nationwide
    0.19
    Activations Density 0.005%

    No Known Activations