© 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. 14976
    Prev
    Next
    INDEX
    Explanations

    asm id

    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
    leaning
    -0.23
    妨
    -0.22
    itar
    -0.21
    æĸ¹éĴĪ
    -0.20
    æ´ĩ
    -0.20
    annies
    -0.19
    MORE
    -0.19
    bih
    -0.19
    /Grid
    -0.18
    ahoma
    -0.18
    POSITIVE LOGITS
    è½½ä½ĵ
    0.22
    æİ¥è¿ĩ
    0.21
    大çīĩ
    0.20
    è¼ī
    0.20
    åĪĽå§ĭ
    0.20
    ç»ıå¼Ģ
    0.20
    _package
    0.19
    å¼ĢåĪĽ
    0.19
     IRepository
    0.19
    ä½
    0.18
    Activations Density 0.154%

    No Known Activations