© 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. 14067
    Prev
    Next
    INDEX
    Explanations

    scientific publications

    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
    å®
    -0.24
    æŃ£å¦Ĥ
    -0.21
    #undef
    -0.20
    为ä¹ĭ
    -0.19
    åįĥéĩĮ
    -0.19
    zu
    -0.19
    åIJİèĢħ
    -0.19
    è´¢æĬ¥
    -0.19
    è¿Ļ项
    -0.18
    ooks
    -0.18
    POSITIVE LOGITS
    ä¸į对
    0.20
    _attempt
    0.19
    SectionsIn
    0.19
    âĢĹ
    0.19
    éĢļè¿ĩ对
    0.18
    ï¼ĩ
    0.18
    \\/
    0.18
     Mack
    0.18
     tet
    0.17
     repro
    0.17
    Activations Density 0.080%

    No Known Activations