© 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. 11306
    Prev
    Next
    INDEX
    Explanations

    Hello dear, what, love, getting

    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
    究
    -0.22
    åĵ©
    -0.20
    åĿĬ
    -0.20
    ç²
    -0.19
    ipl
    -0.19
    éĢ
    -0.19
    ort
    -0.19
    åĸ½
    -0.19
    袪
    -0.18
    嬴
    -0.18
    POSITIVE LOGITS
    å¦Ĥæŀľæĺ¯
    0.20
    losures
    0.19
    æĤ¨å¥½
    0.18
    ä¸Ģåı£æ°Ķ
    0.18
    å¾Ĺ天
    0.18
    æĹ¢çĦ¶
    0.18
    èµŀåIJĮ
    0.18
    ãģĶè¦
    0.18
    åľºä¸Ĭ
    0.18
    æĪijåĸľæ¬¢
    0.17
    Activations Density 0.021%

    No Known Activations