© 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. 16413
    Prev
    Next
    INDEX
    Explanations

    online services

    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
    éĺ¶çº§
    -0.22
    é£ŀæī¬
    -0.20
    ç¼ī
    -0.20
    cia
    -0.19
    ä¸Ģ个人
    -0.19
    åĩºèº«
    -0.19
    解åĨ³
    -0.18
    åIJĵ
    -0.18
    ä½ľä¸ļ
    -0.18
    arness
    -0.18
    POSITIVE LOGITS
    æŃ£å¸¸ä½¿çĶ¨
    0.19
    usage
    0.19
    /services
    0.18
    Apis
    0.18
    RelativeTo
    0.18
    æħ£
    0.18
    ouncer
    0.17
    NASDAQ
    0.17
    pecific
    0.17
    鬯
    0.17
    Activations Density 0.028%

    No Known Activations