© 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. 13655
    Prev
    Next
    INDEX
    Explanations

    built buildings

    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
    龸çİĭ
    -0.23
    åľ¨ä»Ĭå¹´
    -0.21
    æĬĸ
    -0.21
    èĩªå¦Ĥ
    -0.20
    泡泡
    -0.20
    åij¼
    -0.19
     invent
    -0.19
     lately
    -0.18
    åľ¨åħ¨çIJĥ
    -0.18
    é¾Į
    -0.18
    POSITIVE LOGITS
    建éĢł
    0.35
    修建
    0.32
    å§ĭ建
    0.30
    å®Įå·¥
    0.28
    å§ĭ建äºİ
    0.27
    建æĪIJ
    0.27
    åħ´å»º
    0.26
    å·¥åĮł
    0.26
    åĩºèµĦ
    0.25
    æĶ¹å»º
    0.25
    Activations Density 0.129%

    No Known Activations