© 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. 11891
    Prev
    Next
    INDEX
    Explanations

    To + action verb

    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
    /or
    -0.23
    åĨįä¹Ł
    -0.19
    ÑĢей
    -0.18
    è¦ģä¹Ī
    -0.18
    pdata
    -0.18
    åIJĦé¡¹å·¥ä½ľ
    -0.18
    duct
    -0.17
     паÑĢа
    -0.17
    ttp
    -0.17
    -0.16
    POSITIVE LOGITS
    形象
    0.26
    ç¡®ä¿Ŀ
    0.22
    çIJĨ解
    0.21
    äºĨè§£æĽ´å¤ļ
    0.20
    æŁ¥çľĭæĽ´å¤ļ
    0.20
    缮çļĦ
    0.20
    æĬ½æ£Ģ
    0.20
    åĽŀçŃĶ
    0.20
     Ñĩего
    0.19
    æľīå¿ħè¦ģ
    0.19
    Activations Density 0.068%

    No Known Activations