© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12436
    Prev
    Next
    INDEX
    Explanations

    academic science disciplines

    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
    illard
    -0.18
    nova
    -0.18
    kea
    -0.18
    æłª
    -0.17
    åij¨åĽ´
    -0.17
    åį°è±¡æ·±åĪ»
    -0.17
    éĢıæĺİ
    -0.17
    _advanced
    -0.17
    å½ĵåīįä½įç½®
    -0.17
    ยา
    -0.17
    POSITIVE LOGITS
     ÙĪاÙĦØŃ
    0.20
    apus
    0.19
    海绵
    0.18
    åĬĽæ±Ĥ
    0.18
    Spacing
    0.17
    æĶ¿æ²»
    0.17
    upy
    0.17
    Cond
    0.17
    èĪªç©ºèĪªå¤©
    0.17
     Chung
    0.16
    Activations Density 0.017%

    No Known Activations