© 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. 12977
    Prev
    Next
    INDEX
    Explanations

    keywords and ISSN

    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
    ä¿Ŀç¨İ
    -0.20
    _tick
    -0.19
    缴æĴŃéĹ´
    -0.19
    æģ°å¥½
    -0.19
    ULD
    -0.18
    UIL
    -0.18
     ÑĥÑģп
    -0.18
    ADI
    -0.18
    orted
    -0.18
    otify
    -0.17
    POSITIVE LOGITS
    éļ¾åıĹ
    0.21
    æłī
    0.21
    æ´¾
    0.21
    å¢ī
    0.21
    湿度
    0.21
    个人è§ĤçĤ¹
    0.20
    æ¤ħåŃIJ
    0.19
    ä¿
    0.19
    æ°ĶåĢĻ
    0.19
    çļ±
    0.19
    Activations Density 0.002%

    No Known Activations