© 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. 10457
    Prev
    Next
    INDEX
    Explanations

    check if missing

    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
    为äºĨ让
    -0.22
    odont
    -0.22
    è¯Ħå®ļ
    -0.21
    èĪ£
    -0.20
    å²Ľä¸Ĭ
    -0.20
    igi
    -0.19
    odon
    -0.19
    asu
    -0.19
    ç¥ľ
    -0.19
     buck
    -0.19
    POSITIVE LOGITS
    æľī没æľī
    0.27
    æĺ¯åIJ¦æľī
    0.22
    è«
    0.21
     ÑģкаÑĩ
    0.20
    æĺ¯åIJ¦
    0.20
     unzip
    0.19
    å®ŀåľ¨æĺ¯
    0.18
    è¿ijæľŁ
    0.18
    erk
    0.18
     nevertheless
    0.18
    Activations Density 0.009%

    No Known Activations