© 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. 11541
    Prev
    Next
    INDEX
    Explanations

    school and internship experiences

    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
     baÅŁÄ±na
    -0.21
    arus
    -0.21
    orado
    -0.20
    æľ¬è½®
    -0.20
    çĤ·
    -0.19
    çļĩåŃIJ
    -0.18
    ä¼ļéķ¿
    -0.18
    å¤ļå¤ļ
    -0.18
    æĿ¥çļĦ
    -0.18
    è¿ĽéŨ
    -0.18
    POSITIVE LOGITS
    æľŁ
    0.24
    éĺ¶æ®µ
    0.22
    åľ¨é¦Ļ港
    0.21
    æ´»
    0.21
    _was
    0.20
    è£ı
    0.20
    缴èĩ³
    0.20
    æĹ¶æľŁ
    0.20
    æľŁéĹ´
    0.19
    åħĪåIJİ
    0.19
    Activations Density 0.070%

    No Known Activations