© 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. 10783
    Prev
    Next
    INDEX
    Explanations

    internet explorer versions

    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
    åĨĴ
    -0.22
    åIJģ
    -0.21
    岸边
    -0.20
    麻辣
    -0.20
    åħļçļĦé¢Ĩ导
    -0.19
    ä¸Ģå®ļèĥ½
    -0.19
    ä¸Ģçľ¼
    -0.19
    æİĪäºĪ
    -0.19
    çĸıéĢļ
    -0.18
    iron
    -0.18
    POSITIVE LOGITS
    份
    0.19
    ÎĻ
    0.18
    suite
    0.18
    \Factory
    0.18
    ipes
    0.18
    WARDS
    0.17
    ÙĦس
    0.17
    GINE
    0.17
    око
    0.17
    ritch
    0.17
    Activations Density 0.051%

    No Known Activations