© 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. 13124
    Prev
    Next
    INDEX
    Explanations

    code comments and definitions

    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
    éĢļ
    -0.21
     number
    -0.20
     universal
    -0.20
     throughout
    -0.20
     shadow
    -0.19
     ...
    -0.19
    åĪĩ
    -0.19
     stem
    -0.19
    -0.19
    ichel
    -0.19
    POSITIVE LOGITS
    .echo
    0.23
    åĩłåı¥
    0.22
    èĩªè±ª
    0.22
    çªģå¦Ĥåħ¶
    0.21
    .ov
    0.21
    没è§ģè¿ĩ
    0.21
    åIJĵå¾Ĺ
    0.20
    æĸ°äººçݩ家
    0.20
    åĢĴéľī
    0.20
    åľ¨çݩ家ä¸Ń
    0.20
    Activations Density 0.003%

    No Known Activations