© 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. 16928
    Prev
    Next
    INDEX
    Explanations

    passed on to generations

    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
    ville
    -0.20
    éĹ®é¢ĺæĺ¯
    -0.20
    Æ¡
    -0.20
    è°ĥ
    -0.19
    inium
    -0.19
    èıŁ
    -0.19
     League
    -0.19
    è¹ĭ
    -0.19
    VILLE
    -0.19
    öne
    -0.19
    POSITIVE LOGITS
    ä¼łæī¿
    0.40
    çĽ¸ä¼ł
    0.36
     traditions
    0.30
     tradition
    0.28
    ä¸ĭæĿ¥çļĦ
    0.28
    ä¸Ģ代
    0.26
    ä¼łéĢĴ
    0.24
    trad
    0.24
     generations
    0.22
    Trad
    0.22
    Activations Density 0.026%

    No Known Activations