© 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. 11525
    Prev
    Next
    INDEX
    Explanations

    subject to

    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
    æį§
    -0.21
    ç´ł
    -0.20
    opus
    -0.19
     ÙħÙĤابÙĦ
    -0.19
    lation
    -0.19
    sse
    -0.18
    vore
    -0.18
    throp
    -0.18
     важ
    -0.17
    anio
    -0.17
    POSITIVE LOGITS
    éªĭ
    0.21
    æ®ģ
    0.20
    é©·
    0.19
    èĩªè´Ł
    0.19
    éģIJ
    0.19
     trách
    0.19
    é£İäºij
    0.19
    æĪIJéķ¿ä¸º
    0.19
    äºīè®®
    0.19
    ellig
    0.18
    Activations Density 0.019%

    No Known Activations