© 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. 13596
    Prev
    Next
    INDEX
    Explanations

    v. case citations

    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
    æīİå®ŀ
    -0.22
    ç»´å¥ĩ
    -0.20
     диÑĢ
    -0.19
    yat
    -0.18
    CT
    -0.18
     ë¬¼ë¡ł
    -0.18
    bor
    -0.18
     local
    -0.18
    Bug
    -0.18
    éĢĢ
    -0.18
    POSITIVE LOGITS
    ãĤ±ãĥ¼ãĤ¹
    0.21
    åѦ龸
    0.20
    åŃĹåı·
    0.20
    驳
    0.20
    çī²
    0.20
    xdb
    0.20
     Stunning
    0.20
    该æ¡Ī
    0.19
    ä½ļ
    0.19
    åĽ½åĬ¡
    0.19
    Activations Density 0.267%

    No Known Activations