© 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. 11334
    Prev
    Next
    INDEX
    Explanations

    anything but

    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
    æľŁéĹ´
    -0.21
    æ¿®
    -0.21
    ä¹Łæľīä¸ĢäºĽ
    -0.19
    èijĨ
    -0.18
    contre
    -0.18
    份
    -0.18
    æľŁéĸĵ
    -0.18
    openh
    -0.18
     многиÑħ
    -0.18
    主è§Ĥ
    -0.17
    POSITIVE LOGITS
    ../../
    0.21
    ematic
    0.20
    agan
    0.19
    ery
    0.18
    reeze
    0.18
    éĴŀ
    0.18
    ç«ĻçĿĢ
    0.17
     oper
    0.17
    adium
    0.17
    æŀģ大çļĦ
    0.17
    Activations Density 0.004%

    No Known Activations