© 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. 15036
    Prev
    Next
    INDEX
    Explanations

    parallel universes, realms, dimensions, worlds

    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
    é¢ī
    -0.24
    ÑĦоÑĢ
    -0.21
    æĭ¯
    -0.20
     Athena
    -0.19
    ç»ĻåĩºäºĨ
    -0.19
     Millenn
    -0.19
    à¸Ĥà¸Ļา
    -0.19
    å¸Ĥéķ¿
    -0.19
    ç»Ļåĩº
    -0.18
    è´²
    -0.18
    POSITIVE LOGITS
     reality
    0.30
     realms
    0.27
     realm
    0.25
     realities
    0.23
    çİ°å®ŀ
    0.23
    éĦ£
    0.23
    维度
    0.23
     dimension
    0.22
    çݯå¢ĥä¸Ń
    0.21
     existence
    0.21
    Activations Density 0.046%

    No Known Activations