© 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. 14700
    Prev
    Next
    INDEX
    Explanations

    take advantage

    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
    åĶĩ
    -0.20
    pike
    -0.20
     iNdEx
    -0.19
    antino
    -0.19
    è¿ĩåī©
    -0.19
    /twitter
    -0.19
    ä¸į妨
    -0.19
    odont
    -0.19
    ä¸įéĶĻ
    -0.19
    ä¹ĭ乡
    -0.19
    POSITIVE LOGITS
    çīŁ
    0.22
    éļIJèĹı
    0.21
     payload
    0.20
    åĩĮ
    0.20
    çªĥ
    0.20
    窥
    0.20
    æľªç»ıæİĪæĿĥ
    0.20
    éĺ²å¾¡
    0.19
    åħ¨æł¡
    0.19
    åį±å®³
    0.19
    Activations Density 0.027%

    No Known Activations