© 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. 13290
    Prev
    Next
    INDEX
    Explanations

    then you

    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
    ä¸Ģæĸ¹éĿ¢
    -0.22
     bare
    -0.22
    ë§Į
    -0.21
    ä½Ĩè¿Ļ
    -0.18
    éĥ¨åĪĨ
    -0.18
    erno
    -0.18
    jr
    -0.18
    ä½ĨæĪij
    -0.17
    bare
    -0.17
     Tob
    -0.17
    POSITIVE LOGITS
    éĢĤåIJĪèĩªå·±
    0.21
    åĪ©åĻ¨
    0.21
    åİĮ
    0.21
    ëĿ¼ë©´
    0.20
    é¦ĸéĢī
    0.20
    ç¥ŀåĻ¨
    0.20
    æľĢåIJĪéĢĤ
    0.20
    å°±éľĢè¦ģ
    0.19
    çıŃåŃIJ
    0.19
    åĪ½
    0.19
    Activations Density 0.093%

    No Known Activations