© 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. 14254
    Prev
    Next
    INDEX
    Explanations

    movie titles

    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
    arms
    -0.19
     Kra
    -0.18
     Karnataka
    -0.18
     Armstrong
    -0.18
    ç´¯äºĨ
    -0.18
    åį«
    -0.18
     retract
    -0.17
    æĮ¡ä½ı
    -0.17
    åī©
    -0.17
    ober
    -0.17
    POSITIVE LOGITS
    æĶ¯æŁ±
    0.21
    adro
    0.20
    综åIJĪæĢ§
    0.20
    为ä»Ģä¹Īä¸į
    0.18
    åľľ
    0.18
    icter
    0.18
    åħ¨æĹ¥
    0.18
    ertz
    0.18
    ähr
    0.18
    quete
    0.17
    Activations Density 0.210%

    No Known Activations