© 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. 15496
    Prev
    Next
    INDEX
    Explanations

    blog posts

    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
     Guinness
    -0.20
    åĭĴ
    -0.20
    çĿ¥
    -0.20
    nable
    -0.20
    ẹ
    -0.19
    éra
    -0.19
    _placeholder
    -0.19
     ëĭ¹ìĭľ
    -0.18
    ½
    -0.18
    /LICENSE
    -0.18
    POSITIVE LOGITS
    åįļ客
    0.25
     blog
    0.22
    æ¯ĶæĪij
    0.21
    ä¸Ģç¯ĩ
    0.21
    è§ģ解
    0.20
    udoku
    0.19
     blogs
    0.19
     Plate
    0.19
     Hom
    0.19
     Function
    0.19
    Activations Density 0.028%

    No Known Activations