© 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. 10481
    Prev
    Next
    INDEX
    Explanations

    sounds like

    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
    éķľå¤´
    -0.20
    æĶ¹éĿ©åıijå±ķ
    -0.20
    ä¸Ģçľ¼
    -0.18
    è§Ĩè§Ĵ
    -0.18
    ariate
    -0.18
    Ont
    -0.17
    ulton
    -0.17
     иÑģÑĤ
    -0.17
    andi
    -0.17
    ustr
    -0.17
    POSITIVE LOGITS
    åIJ¬èµ·æĿ¥
    0.23
    sounds
    0.23
     Sounds
    0.22
    éŁ¿
    0.21
    åĵį
    0.20
    tracked
    0.20
    alar
    0.20
     sounds
    0.19
    èĢ³è¾¹
    0.19
    èĮ¬
    0.18
    Activations Density 0.012%

    No Known Activations