© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 10669
    Prev
    Next
    INDEX
    Explanations

    apple products and devices

    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
    sell
    -0.19
     Fet
    -0.18
    éĤij
    -0.18
    ohan
    -0.18
    regor
    -0.18
    ê´Ħ
    -0.18
    é¡¿
    -0.18
    åĪij
    -0.18
    åħģ
    -0.18
    angi
    -0.17
    POSITIVE LOGITS
    zech
    0.22
    åĬłå¿«å»ºè®¾
    0.21
    éĺµèIJ¥
    0.21
    们çļĦ
    0.21
    å¿ĥåĬ¨
    0.20
    åĪĴç®Ĺ
    0.19
    ç½ijç«Ļ建设
    0.19
    éĨ®
    0.18
    åıijå¸ĥæŶéĹ´
    0.18
     COLORS
    0.18
    Activations Density 0.005%

    No Known Activations