© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12236
    Prev
    Next
    INDEX
    Explanations

    chapter numbers or roman numerals

    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
    è¿©
    -0.20
    :\/\/
    -0.19
    æŀ¢
    -0.19
    ä¸Ĭçľĭ
    -0.19
    åĪ¸
    -0.19
     Publications
    -0.19
    GRAM
    -0.19
    grad
    -0.18
    èĭıå·ŀ
    -0.18
    çİ
    -0.18
    POSITIVE LOGITS
    inery
    0.21
    æ¯Ĵ
    0.20
    许
    0.19
    æµģ
    0.19
    UNCH
    0.19
     bare
    0.19
    æİĴ
    0.19
    çŀ»
    0.19
    É´
    0.18
    -ar
    0.17
    Activations Density 0.004%

    No Known Activations