© 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. 15565
    Prev
    Next
    INDEX
    Explanations

    names of things or places

    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
    æ´¾
    -0.20
    èįī
    -0.19
    éħĮ
    -0.18
    æĺŁçIJĥ
    -0.17
    Ñİ
    -0.17
    ÑĢак
    -0.17
    ober
    -0.16
    å¼ķ
    -0.16
    Cars
    -0.16
     hÃłnh
    -0.16
    POSITIVE LOGITS
    @yahoo
    0.23
    @gmail
    0.21
    æĹıèĩªæ²»åİ¿
    0.20
    æĹıèĩªæ²»å·ŀ
    0.18
    eway
    0.18
     Pvt
    0.18
    çļĦåĸľçĪ±
    0.18
    æľ¬ç¶²ç«Ļ
    0.18
    å¢ħ
    0.17
    æĪijå¿ĥéĩĮ
    0.17
    Activations Density 0.355%

    No Known Activations