© 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. 13953
    Prev
    Next
    INDEX
    Explanations

    software setup

    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
    ResultSet
    -0.21
     Vacuum
    -0.19
     vacuum
    -0.18
    .heroku
    -0.18
    (EXPR
    -0.18
    isson
    -0.18
    .quote
    -0.18
    -owner
    -0.18
     stranded
    -0.18
     hã
    -0.17
    POSITIVE LOGITS
    é¢ľåĢ¼
    0.23
    çļĦä»»åĬ¡
    0.22
    åįłåľ°éĿ¢ç§¯
    0.21
    ç»ĥ
    0.21
    Windows
    0.21
     Windows
    0.21
    /windows
    0.21
    ä¿¡ä»°
    0.20
    èĭ·
    0.19
    æĹłæĦı
    0.19
    Activations Density 0.010%

    No Known Activations