© 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. 15624
    Prev
    Next
    INDEX
    Explanations

    sounds like

    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
    åĪĨåĪ«æĺ¯
    -0.21
    ä¸įä¿¡
    -0.21
    åıªä¸º
    -0.21
    å¥ĸ
    -0.20
    æıī
    -0.20
    éļı便
    -0.18
    çİ©æĦı
    -0.18
    Fuck
    -0.18
    ulong
    -0.18
    поÑĩ
    -0.18
    POSITIVE LOGITS
     indeed
    0.30
    ç¡®å®ŀ
    0.24
    çļĦç¡®
    0.23
     certainly
    0.23
     дейÑģÑĤвиÑĤелÑĮно
    0.21
    RIX
    0.20
    ç¡®å®ŀæĺ¯
    0.19
     Rush
    0.19
    確實
    0.19
     Indeed
    0.19
    Activations Density 0.073%

    No Known Activations