© 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. 11461
    Prev
    Next
    INDEX
    Explanations

    words that end in ued

    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
    idad
    -0.18
    Mor
    -0.18
    寮
    -0.18
    isko
    -0.18
    以éĺ²
    -0.18
    arching
    -0.17
    éĴ¿
    -0.17
     tens
    -0.17
    å¾Īå¤ļ人éĥ½
    -0.17
    -bottom
    -0.17
    POSITIVE LOGITS
    çŃĶ辩
    0.20
    åİħ
    0.20
    æĹ¥æľŁ
    0.20
    温室
    0.19
    æĮĩ导æĦıè§ģ
    0.18
     ngÃły
    0.18
    å®ļæľŁ
    0.18
    åѦä½į
    0.18
    åĽ´çĿĢ
    0.18
    IFI
    0.18
    Activations Density 0.035%

    No Known Activations