© 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. 10579
    Prev
    Next
    INDEX
    Explanations

    camera and phone 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
    Negative Logits
    æ¡Ģ
    -0.19
    моÑĤ
    -0.19
    èķ¨
    -0.19
    æīijåħĭ
    -0.19
    /ws
    -0.18
     bart
    -0.18
    çĦ
    -0.18
    eted
    -0.18
    hn
    -0.18
     moto
    -0.18
    POSITIVE LOGITS
    สาย
    0.21
    åĥµ
    0.20
    泯
    0.20
    åħį
    0.18
    æľ¯
    0.18
    ãģĿãĤĮãģ§ãĤĤ
    0.18
    Shortcut
    0.18
    å¼±
    0.18
    éķĢ
    0.18
    æŀģèĩ´
    0.18
    Activations Density 0.003%

    No Known Activations