© 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. 14322
    Prev
    Next
    INDEX
    Explanations

    another such

    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
    è¾ĪåŃIJ
    -0.23
    è°¤
    -0.19
     <!--[
    -0.19
     Throne
    -0.19
    çŁ¥åIJįåĵģçīĮ
    -0.18
    ÂŃs
    -0.18
    è´¥
    -0.18
    tal
    -0.18
     Conse
    -0.17
    ä¹ł
    -0.17
    POSITIVE LOGITS
    以åıĬåħ¶ä»ĸ
    0.20
    æIJŃ
    0.19
    åľ¨ä¸ĢæĹģ
    0.19
    å¥Ĺè·¯
    0.18
    Linked
    0.18
    vil
    0.18
    åºĸ
    0.18
    个æĢ§
    0.18
    ä»ĬåĽŀãģ¯
    0.17
    æıIJåĪ°
    0.17
    Activations Density 0.201%

    No Known Activations