© 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. 16907
    Prev
    Next
    INDEX
    Explanations

    submissions and proposals

    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
     inn
    -0.19
     lit
    -0.19
    åľ¨ä¸Ģèµ·
    -0.17
    çĶ¨åĵģ
    -0.17
    -columns
    -0.17
     gre
    -0.17
     brackets
    -0.17
     justice
    -0.17
    åįĸæİī
    -0.17
     rh
    -0.17
    POSITIVE LOGITS
    haul
    0.23
    é©·
    0.22
    èĥ½åĬĽå¼º
    0.20
    heets
    0.19
    [at
    0.19
    绪
    0.19
    å¸ĺ
    0.19
    çī¡
    0.18
    æĮŀ
    0.18
    \uc
    0.18
    Activations Density 0.022%

    No Known Activations