© 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. 11492
    Prev
    Next
    INDEX
    Explanations

    accept or agree

    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
    ä»ĸèĩªå·±
    -0.22
     Americ
    -0.21
    ç»IJ
    -0.20
    Edited
    -0.20
    ish
    -0.19
    era
    -0.19
    è°Ĭ
    -0.19
     distr
    -0.19
    åľ¨å¤ĸéĿ¢
    -0.18
    scape
    -0.18
    POSITIVE LOGITS
    /ag
    0.21
    ä¸įåIJĮæĦı
    0.20
    è¿Ļ份
    0.20
    çŃ¾ç½²
    0.19
    gba
    0.19
    agar
    0.18
     Microsystems
    0.18
    (signature
    0.18
    variants
    0.18
    VILLE
    0.18
    Activations Density 0.049%

    No Known Activations