© 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. 10858
    Prev
    Next
    INDEX
    Explanations

    quantity followed by of

    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
    odian
    -0.21
    èĢĮè¨Ģ
    -0.21
     McL
    -0.19
    ILED
    -0.19
    lı
    -0.19
    à¹Ĩ
    -0.19
    \↵
    -0.18
    oub
    -0.18
     America
    -0.18
    çļĦä¸Ģ
    -0.18
    POSITIVE LOGITS
    åIJį为
    0.20
    欢åij¼
    0.20
    äºĴè¡¥
    0.20
    第äºĮç§į
    0.19
    ä¼´ä¾£
    0.18
    çŁ³æ¦´
    0.18
    æĸ«
    0.18
     Whip
    0.18
    éĢĤå½ĵ
    0.18
    å¿ĥ仪
    0.18
    Activations Density 0.011%

    No Known Activations