© 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. 12953
    Prev
    Next
    INDEX
    Explanations

    water activities

    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
    鹪
    -0.22
    èļ¯
    -0.21
    æ¸ħåĩī
    -0.20
    æļ´é£İ
    -0.20
    rics
    -0.20
    è¾Ľè¾£
    -0.20
    _chip
    -0.19
    åıijçĥŃ
    -0.19
    èIJ¤
    -0.19
    å·¢
    -0.18
    POSITIVE LOGITS
    æ°´éĿ¢
    0.22
    姿åĬ¿
    0.21
    çľĭçĤ¹
    0.21
    缮çļĦ
    0.20
    ä¸ĢåŃĹ
    0.20
    éĹ¾
    0.20
    åĪ«å¢ħ
    0.19
    shore
    0.19
    _FUN
    0.19
     rope
    0.19
    Activations Density 0.003%

    No Known Activations