© 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. 16887
    Prev
    Next
    INDEX
    Explanations

    porous silica, RO vessel, hollow tube

    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
     Halo
    -0.20
    æŃĨ
    -0.20
    ç»Ĺ
    -0.20
    æİ¥
    -0.19
    .hr
    -0.19
    çĶŁäº§è½¦éĹ´
    -0.19
    åĸĿæ°´
    -0.19
    åĬłä¹ĭ
    -0.18
    忽
    -0.18
     halo
    -0.18
    POSITIVE LOGITS
    åŀĭ
    0.20
    ä¸Ģä½ĵ
    0.20
    jang
    0.19
    ServerError
    0.19
     ordinary
    0.18
    éĢı
    0.18
     opaque
    0.18
    ItemAt
    0.18
    .isSuccess
    0.17
     Äijá»ķ
    0.17
    Activations Density 0.029%

    No Known Activations